Leaderboard Explore Compare Profile Community Blog FAQ Competition 2024 Report Issue

convnext_base:clip_laiona_augreg_ft_in1k_384

Contributed by Anonymous User No reference provided Find on GitHub source Compare this model

CNN

88.6M parameters

384 × 384 input

Contrastive + supervised Apache-2.0

Scores on benchmarks

from scoring API

Model rank shown below is with respect to all public models.

.436	average_vision rank 6 138 benchmarks	.436 0 ceiling best median

.332	neural_vision rank 46 77 benchmarks	.332 0 ceiling best median

.422	V1 rank 29 33 benchmarks	.422 0 ceiling best median

.354	Allen2022_fmri_surface.V1 rank 50 2 benchmarks	.354 0 ceiling best median

.214	Allen2022_fmri_surface.V1-rdm v1 [reference] rank 71	.214 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.494	Allen2022_fmri_surface.V1-ridge v1 [reference] rank 32	.494 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.213	FreemanZiemba2013.V1-pls v3 [reference] rank 364	.213 0 ceiling best median
	recordings from 102 sites in V1 315 images Sample stimuli cannot be displayed publicly for this benchmark.

.610	Hebart2023_fmri.V1-ridgecv v3 rank 34	.610 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.310	Li2026.V1 rank 36 2 benchmarks	.310 0 ceiling best median

.251	Li2026.V1-rdm v1 [reference] rank 25	.251 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.369	Li2026.V1-ridgecv v1 [reference] rank 62	.369 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.707	Marques2020 [reference] rank 205 22 benchmarks	.707 0 ceiling best median

.945	V1-orientation rank 7 7 benchmarks	.945 0 ceiling best median

.963	Marques2020_DeValois1982-pref_or v1 rank 148	.963 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.909	Marques2020_Ringach2002-circular_variance v1 rank 62	.909 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.925	Marques2020_Ringach2002-cv_bandwidth_ratio v1 rank 49	.925 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.989	Marques2020_Ringach2002-opr_cv_diff v1 rank 2	.989 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.950	Marques2020_Ringach2002-or_bandwidth v1 rank 16	.950 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.966	Marques2020_Ringach2002-or_selective v1 rank 175	.966 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.911	Marques2020_Ringach2002-orth_pref_ratio v1 rank 51	.911 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.698	V1-receptive_field_size rank 136 2 benchmarks	.698 0 ceiling best median

.590	Marques2020_Cavanaugh2002-grating_summation_field v1 [reference] rank 296	.590 0 ceiling best median
	2304 images Sample stimuli cannot be displayed publicly for this benchmark.

.807	Marques2020_Cavanaugh2002-surround_diameter v1 [reference] rank 39	.807 0 ceiling best median
	2304 images Sample stimuli cannot be displayed publicly for this benchmark.

.908	V1-response_magnitude rank 116 3 benchmarks	.908 0 ceiling best median

.903	Marques2020_FreemanZiemba2013-max_noise v1 [reference] rank 79	.903 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.846	Marques2020_FreemanZiemba2013-max_texture v1 [reference] rank 231	.846 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.973	Marques2020_Ringach2002-max_dc v1 rank 109	.973 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.681	V1-response_selectivity rank 142 4 benchmarks	.681 0 ceiling best median

.841	Marques2020_FreemanZiemba2013-texture_selectivity v1 [reference] rank 59	.841 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.680	Marques2020_FreemanZiemba2013-texture_sparseness v1 [reference] rank 235	.680 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.749	Marques2020_FreemanZiemba2013-texture_variance_ratio v1 [reference] rank 173	.749 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.452	Marques2020_Ringach2002-modulation_ratio v1 rank 260	.452 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.535	V1-spatial_frequency rank 403 3 benchmarks	.535 0 ceiling best median

.529	Marques2020_DeValois1982-peak_sf v1 rank 359	.529 0 ceiling best median
	2112 images Sample stimuli cannot be displayed publicly for this benchmark.

.664	Marques2020_Schiller1976-sf_bandwidth v1 [reference] rank 358	.664 0 ceiling best median
	2112 images Sample stimuli cannot be displayed publicly for this benchmark.

.413	Marques2020_Schiller1976-sf_selective v1 [reference] rank 414	.413 0 ceiling best median
	2112 images Sample stimuli cannot be displayed publicly for this benchmark.

.615	V1-surround_modulation rank 232 1 benchmark	.615 0 ceiling best median

.615	Marques2020_Cavanaugh2002-surround_suppression_index v1 [reference] rank 232	.615 0 ceiling best median
	2304 images Sample stimuli cannot be displayed publicly for this benchmark.

.571	V1-texture_modulation rank 300 2 benchmarks	.571 0 ceiling best median

.452	Marques2020_FreemanZiemba2013-abs_texture_modulation_index v1 [reference] rank 311	.452 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.689	Marques2020_FreemanZiemba2013-texture_modulation_index v1 [reference] rank 277	.689 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.809	Papale2025.V1-ridgecv v3 [reference] rank 10	.809 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.027	Coggan2024_fMRI.V1-rdm v1 rank 213	.027 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.344	Zerbe2026_fmri.V1 [reference] rank 41 3 benchmarks	.344 0 ceiling best median

.330	Zerbe2026_fmri.V1-ood-ridgecv v1 [reference] rank 85	.330 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.243	Zerbe2026_fmri.V1-rdm-pearson v1 [reference] rank 54	.243 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.458	Zerbe2026_fmri.V1-tau-ridgecv v1 [reference] rank 27	.458 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.278	V2 rank 102 10 benchmarks	.278 0 ceiling best median

.338	Allen2022_fmri_surface.V2 rank 78 2 benchmarks	.338 0 ceiling best median

.209	Allen2022_fmri_surface.V2-rdm v1 [reference] rank 103	.209 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.468	Allen2022_fmri_surface.V2-ridge v1 [reference] rank 68	.468 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.253	FreemanZiemba2013.V2-pls v3 [reference] rank 206	.253 0 ceiling best median
	recordings from 103 sites in V2 315 images Sample stimuli cannot be displayed publicly for this benchmark.

.550	Hebart2023_fmri.V2-ridgecv v3 rank 106	.550 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.109	Li2026.V2 rank 141 2 benchmarks	.109 0 ceiling best median

.048	Li2026.V2-rdm v1 [reference] rank 95	.048 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.169	Li2026.V2-ridgecv v1 [reference] rank 140	.169 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.107	Coggan2024_fMRI.V2-rdm v1 rank 116	.107 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.308	Zerbe2026_fmri.V2 [reference] rank 84 3 benchmarks	.308 0 ceiling best median

.358	Zerbe2026_fmri.V2-ood-ridgecv v1 [reference] rank 62	.358 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.188	Zerbe2026_fmri.V2-rdm-pearson v1 [reference] rank 94	.188 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.380	Zerbe2026_fmri.V2-tau-ridgecv v1 [reference] rank 90	.380 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.290	V4 rank 89 16 benchmarks	.290 0 ceiling best median

.255	Allen2022_fmri_surface.V4 rank 120 2 benchmarks	.255 0 ceiling best median

.152	Allen2022_fmri_surface.V4-rdm v1 [reference] rank 127	.152 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.359	Allen2022_fmri_surface.V4-ridge v1 [reference] rank 110	.359 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.259	Cowley2026.V4-pls v1 [reference] rank 108	.259 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.270	Hebart2023_fmri.V4-ridgecv v3 rank 127	.270 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.111	Li2026.V4 rank 84 2 benchmarks	.111 0 ceiling best median

.079	Li2026.V4-rdm v1 [reference] rank 88	.079 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.143	Li2026.V4-ridgecv v1 [reference] rank 95	.143 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.016	MajajHong2015public.V4-reverse_pls v4 [reference] rank 116	.016 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.530	MajajHong2015.V4-pls v4 [reference] rank 79	.530 0 ceiling best median
	recordings from 88 sites in V4 2560 images Sample stimuli cannot be displayed publicly for this benchmark.

.541	Papale2025.V4-ridgecv v3 [reference] rank 87	.541 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.547	Sanghavi2020.V4-pls v2 [reference] rank 262	.547 0 ceiling best median
	recordings from 47 sites in V4 5760 images Sample stimuli cannot be displayed publicly for this benchmark.

.442	SanghaviJozwik2020.V4-pls v2 [reference] rank 268	.442 0 ceiling best median
	recordings from 50 sites in V4 4916 images Sample stimuli cannot be displayed publicly for this benchmark.

.217	SanghaviMurty2020.V4-pls v2 [reference] rank 142	.217 0 ceiling best median
	recordings from 46 sites in V4 300 images Sample stimuli cannot be displayed publicly for this benchmark.

.021	Coggan2024_fMRI.V4-rdm v1 rank 186	.021 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.269	Zerbe2026_fmri.V4 [reference] rank 97 3 benchmarks	.269 0 ceiling best median

.354	Zerbe2026_fmri.V4-ood-ridgecv v1 [reference] rank 106	.354 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.143	Zerbe2026_fmri.V4-rdm-pearson v1 [reference] rank 98	.143 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.310	Zerbe2026_fmri.V4-tau-ridgecv v1 [reference] rank 90	.310 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.340	IT rank 28 18 benchmarks	.340 0 ceiling best median

.428	Allen2022_fmri_surface.IT rank 30 2 benchmarks	.428 0 ceiling best median

.366	Allen2022_fmri_surface.IT-rdm v1 [reference] rank 21	.366 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.491	Allen2022_fmri_surface.IT-ridge v1 [reference] rank 53	.491 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.253	Bracci2019.anteriorVTC-rdm v1 rank 150	.253 0 ceiling best median
	27 images Sample stimuli cannot be displayed publicly for this benchmark.

.269	Gifford2022.IT-ridgecv v3 [reference] rank 6	.269 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.333	Hebart2023_fmri.IT-ridgecv v3 rank 19	.333 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.305	Li2026.IT rank 66 2 benchmarks	.305 0 ceiling best median

.362	Li2026.IT-rdm v1 [reference] rank 75	.362 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.247	Li2026.IT-ridgecv v1 [reference] rank 39	.247 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.434	MajajHong2015.IT-pls v4 [reference] rank 170	.434 0 ceiling best median
	recordings from 168 sites in IT 2560 images Sample stimuli cannot be displayed publicly for this benchmark.

.080	MajajHong2015public.IT-reverse_pls v4 [reference] rank 47	.080 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.574	Papale2025.IT-ridgecv v3 [reference] rank 34	.574 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.469	Sanghavi2020.IT-pls v2 [reference] rank 76	.469 0 ceiling best median
	recordings from 88 sites in IT 5760 images Sample stimuli cannot be displayed publicly for this benchmark.

.426	SanghaviJozwik2020.IT-pls v2 [reference] rank 193	.426 0 ceiling best median
	recordings from 26 sites in IT 4916 images Sample stimuli cannot be displayed publicly for this benchmark.

.331	SanghaviMurty2020.IT-pls v2 [reference] rank 141	.331 0 ceiling best median
	recordings from 29 sites in IT 300 images Sample stimuli cannot be displayed publicly for this benchmark.

.554	Coggan2024_fMRI.IT-rdm v1 rank 69	.554 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.307	Zerbe2026_fmri.IT [reference] rank 25 3 benchmarks	.307 0 ceiling best median

.228	Zerbe2026_fmri.IT-ood-ridgecv v1 [reference] rank 31	.228 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.371	Zerbe2026_fmri.IT-rdm-pearson v1 [reference] rank 42	.371 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.323	Zerbe2026_fmri.IT-tau-ridgecv v1 [reference] rank 10	.323 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.540	behavior_vision rank 16 61 benchmarks	.540 0 ceiling best median

.528	Rajalingham2018-i2n v2 [reference] rank 115	.528 0 ceiling best median
	match-to-sample task 240 images Sample stimuli cannot be displayed publicly for this benchmark.

.595	Geirhos2021-error_consistency [reference] rank 16 17 benchmarks	.595 0 ceiling best median

.422	Geirhos2021colour-error_consistency v1 [reference] rank 125	.422 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.349	Geirhos2021contrast-error_consistency v1 [reference] rank 81	.349 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.686	Geirhos2021cueconflict-error_consistency v1 [reference] rank 22	.686 0 ceiling best median
	1280 images Sample stimuli cannot be displayed publicly for this benchmark.

1.0	Geirhos2021edge-error_consistency v1 [reference] rank 1	1.0 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.472	Geirhos2021eidolonI-error_consistency v1 [reference] rank 90	.472 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.555	Geirhos2021eidolonII-error_consistency v1 [reference] rank 53	.555 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.511	Geirhos2021eidolonIII-error_consistency v1 [reference] rank 36	.511 0 ceiling best median
	480 images Sample stimuli cannot be displayed publicly for this benchmark.

.256	Geirhos2021falsecolour-error_consistency v1 [reference] rank 180	.256 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.709	Geirhos2021highpass-error_consistency v1 [reference] rank 14	.709 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.516	Geirhos2021lowpass-error_consistency v1 [reference] rank 36	.516 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.621	Geirhos2021phasescrambling-error_consistency v1 [reference] rank 6	.621 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.586	Geirhos2021powerequalisation-error_consistency v1 [reference] rank 26	.586 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.476	Geirhos2021rotation-error_consistency v1 [reference] rank 29	.476 0 ceiling best median
	960 images Sample stimuli cannot be displayed publicly for this benchmark.

.966	Geirhos2021silhouette-error_consistency v1 [reference] rank 18	.966 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.658	Geirhos2021sketch-error_consistency v1 [reference] rank 20	.658 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.750	Geirhos2021stylized-error_consistency v1 [reference] rank 13	.750 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.576	Geirhos2021uniformnoise-error_consistency v1 [reference] rank 43	.576 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.616	Baker2022 rank 42 3 benchmarks	.616 0 ceiling best median

.438	Baker2022fragmented-accuracy_delta v1 [reference] rank 127	.438 0 ceiling best median
	716 images Sample stimuli cannot be displayed publicly for this benchmark.

.713	Baker2022frankenstein-accuracy_delta v1 [reference] rank 56	.713 0 ceiling best median
	716 images Sample stimuli cannot be displayed publicly for this benchmark.

.698	Baker2022inverted-accuracy_delta v1 [reference] rank 38	.698 0 ceiling best median
	360 images Sample stimuli cannot be displayed publicly for this benchmark.

.564	BMD2024 rank 18 4 benchmarks	.564 0 ceiling best median

.582	BMD2024.dotted_1Behavioral-accuracy_distance v1 rank 18	.582 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.465	BMD2024.dotted_2Behavioral-accuracy_distance v1 rank 9	.465 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.600	BMD2024.texture_1Behavioral-accuracy_distance v1 rank 21	.600 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.609	BMD2024.texture_2Behavioral-accuracy_distance v1 rank 18	.609 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.558	Ferguson2024 [reference] rank 60 14 benchmarks	.558 0 ceiling best median

.573	Ferguson2024circle_line-value_delta v1 [reference] rank 62	.573 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

1.0	Ferguson2024color-value_delta v1 [reference] rank 1	1.0 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.839	Ferguson2024convergence-value_delta v1 [reference] rank 41	.839 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.296	Ferguson2024eighth-value_delta v1 [reference] rank 103	.296 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.541	Ferguson2024gray_easy-value_delta v1 [reference] rank 103	.541 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.437	Ferguson2024gray_hard-value_delta v1 [reference] rank 166	.437 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.383	Ferguson2024half-value_delta v1 [reference] rank 195	.383 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.848	Ferguson2024juncture-value_delta v1 [reference] rank 25	.848 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.411	Ferguson2024lle-value_delta v1 [reference] rank 157	.411 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.068	Ferguson2024llh-value_delta v1 [reference] rank 292	.068 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.379	Ferguson2024quarter-value_delta v1 [reference] rank 150	.379 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.961	Ferguson2024round_f-value_delta v1 [reference] rank 21	.961 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.417	Ferguson2024round_v-value_delta v1 [reference] rank 172	.417 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.657	Ferguson2024tilted_line-value_delta v1 [reference] rank 124	.657 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.257	Hebart2023-match v1 rank 173	.257 0 ceiling best median
	1854 images Sample stimuli cannot be displayed publicly for this benchmark.

.574	Kato2026 rank 33 18 benchmarks	.574 0 ceiling best median

.440	Kato2026-error_consistency rank 38 9 benchmarks	.440 0 ceiling best median

.306	Kato2026Ori-error_consistency v1 rank 108	.306 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.392	Kato2026Fil-error_consistency v1 rank 128	.392 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.622	Kato2026Lin-error_consistency v1 rank 28	.622 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.492	Kato2026SilTex-error_consistency v1 rank 42	.492 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.649	Kato2026Sil-error_consistency v1 rank 28	.649 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.871	Kato2026Tex-error_consistency v1 rank 32	.871 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.561	Kato2026LinFil-error_consistency v1 rank 30	.561 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.018	Kato2026Sparse-error_consistency v1 rank 30	.018 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.045	Kato2026Dense-error_consistency v1 rank 50	.045 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.708	Kato2026-accuracy_distance rank 30 9 benchmarks	.708 0 ceiling best median

1.0	Kato2026Ori-accuracy_distance v1 rank 1	1.0 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.800	Kato2026Fil-accuracy_distance v1 rank 125	.800 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.838	Kato2026Lin-accuracy_distance v1 rank 31	.838 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.738	Kato2026SilTex-accuracy_distance v1 rank 47	.738 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.587	Kato2026Sil-accuracy_distance v1 rank 34	.587 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

1.0	Kato2026Tex-accuracy_distance v1 rank 1	1.0 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

1.0	Kato2026LinFil-accuracy_distance v1 rank 1	1.0 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.217	Kato2026Sparse-accuracy_distance v1 rank 40	.217 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.188	Kato2026Dense-accuracy_distance v1 rank 36	.188 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.509	Maniquet2024 rank 180 2 benchmarks	.509 0 ceiling best median

.270	Maniquet2024-confusion_similarity v1 [reference] rank 261	.270 0 ceiling best median
	13600 images Sample stimuli cannot be displayed publicly for this benchmark.

.747	Maniquet2024-tasks_consistency v1 [reference] rank 8	.747 0 ceiling best median
	13600 images Sample stimuli cannot be displayed publicly for this benchmark.

.660	Coggan2024_behavior-ConditionWiseAccuracySimilarity v1 rank 8	.660 0 ceiling best median
	22560 images Sample stimuli cannot be displayed publicly for this benchmark.

.499	engineering_vision rank 25 25 benchmarks	.499 0 ceiling best median

.841	ImageNet-top1 v1 [reference] rank 16	.841 0 ceiling best median
	50000 images Sample stimuli cannot be displayed publicly for this benchmark.

.620	ImageNet-C-top1 [reference] rank 17 4 benchmarks	.620 0 ceiling best median

.597	ImageNet-C-noise-top1 v2 [reference] rank 23	.597 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.525	ImageNet-C-blur-top1 v2 [reference] rank 18	.525 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.681	ImageNet-C-weather-top1 v2 [reference] rank 12	.681 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.677	ImageNet-C-digital-top1 v2 [reference] rank 15	.677 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.750	Geirhos2021-top1 [reference] rank 27 17 benchmarks	.750 0 ceiling best median

.997	Geirhos2021colour-top1 v1 [reference] rank 10	.997 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.990	Geirhos2021contrast-top1 v1 [reference] rank 26	.990 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.281	Geirhos2021cueconflict-top1 v1 [reference] rank 72	.281 0 ceiling best median
	1280 images Sample stimuli cannot be displayed publicly for this benchmark.

.863	Geirhos2021edge-top1 v1 [reference] rank 19	.863 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.519	Geirhos2021eidolonI-top1 v1 [reference] rank 118	.519 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.556	Geirhos2021eidolonII-top1 v1 [reference] rank 99	.556 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.590	Geirhos2021eidolonIII-top1 v1 [reference] rank 83	.590 0 ceiling best median
	480 images Sample stimuli cannot be displayed publicly for this benchmark.

.993	Geirhos2021falsecolour-top1 v1 [reference] rank 18	.993 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.927	Geirhos2021highpass-top1 v1 [reference] rank 21	.927 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.558	Geirhos2021lowpass-top1 v1 [reference] rank 38	.558 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.805	Geirhos2021phasescrambling-top1 v1 [reference] rank 37	.805 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.936	Geirhos2021powerequalisation-top1 v1 [reference] rank 29	.936 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.922	Geirhos2021rotation-top1 v1 [reference] rank 24	.922 0 ceiling best median
	960 images Sample stimuli cannot be displayed publicly for this benchmark.

.638	Geirhos2021silhouette-top1 v1 [reference] rank 34	.638 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.925	Geirhos2021sketch-top1 v1 [reference] rank 15	.925 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.561	Geirhos2021stylized-top1 v1 [reference] rank 48	.561 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.686	Geirhos2021uniformnoise-top1 v1 [reference] rank 42	.686 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.285	Hermann2020 [reference] rank 95 2 benchmarks	.285 0 ceiling best median

.325	Hermann2020cueconflict-shape_bias v1 [reference] rank 132	.325 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.244	Hermann2020cueconflict-shape_match v1 [reference] rank 71	.244 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

How to use

from brainscore_vision import load_model
model = load_model("convnext_base:clip_laiona_augreg_ft_in1k_384")
model.start_task(...)
model.start_recording(...)
model.look_at(...)

Model API

Code examples

Curated metadata

At-a-glance

Architecture: ConvNeXt, pure convolutional neural network
Parameters: 88.6M
Input resolution: 384 × 384 pixels
Recurrent: No
Supervision: Contrastive pretraining + supervised fine tuning
Weights provider: timms
Trainable layers Probable: show confidence source Probable — Existing plugin metadata; primary sources need review.: 113 layers
Checkpoint: timm/convnext_base.clip_laiona_augreg_ft_in1k_384

Training and data

CLIP image-tower weights pretrained in OpenCLIP on LAION, then fine-tuned on ImageNet-1k in timm; naming convention: clip = CLIP-pretrained tower, laiona = LAION-Aesthetic pretrain subset, augreg = AugReg fine-tuning recipe (strong augmentation + regularization), ft_in1k = fine-tuned on ImageNet-1k, 384 = fine-tuned/eval at 384px

Pretrain LAION-Aesthetic

1,281,167

Finetune ImageNet-1k

Objective: Probable: show confidence source Probable — curation workbook: Image-text contrastive pretraining, then classification fine-tuning
Loss:: Not documented
Learning rate:: Not documented
Batch size:: Not documented
Preprocessing: Probable: show confidence source Probable — curation workbook: Model-specific transforms resolved via timm.data.resolve_model_data_config() — standard resize/crop to 384×384 + normalization; exact mean/std not shown on this card

Creators and licensing

Organization:: OpenCLIP
Creators:: Ross Wightman (timm fine-tune); base CLIP-ConvNeXt weights via OpenCLIP team (Ilharco, Wortsman, Wightman, Gordon, Carlini, Taori, Dave, Shankar, Namkoong, Miller, Hajishirzi, Farhadi, Schmidt)
License:: Apache-2.0

Dashed Not documented fields are awaiting curation.

Intended use and limits

Recommended applications

Image classification
feature/embedding extraction
backbone for downstream vision tasks (classification head
feature maps
or pooled embeddings all supported)

Target users

Probable: show confidence source
Probable — curation workbook

ML engineers/researchers needing a strong ImageNet classifier or general-purpose visual feature extractor

Known limitations

Not documented

Biases

Not documented

Brain Encoding Response Generator (BERG)

Through the BERG you can easily generate neural responses to images of your choice using any Brain-Score vision model.

For more information on how to use BERG, see the documentation and tutorial.

Historical trend

Hover the line for a preview; click the chart to pin that month in the sidebar. While pinned, hover does not change it -- use Release or Esc to clear.

Benchmarks BibTeX

@article{allen_massive_2022,
    title = {A massive 7T fMRI dataset to bridge cognitive neuroscience and artificial intelligence},
    volume = {25},
    issn = {1097-6256},
    doi = {10.1038/s41593-021-00962-x},
    journal = {Nature Neuroscience},
    author = {Allen, Emily J. and St-Yves, Ghislain and Wu, Yihan and Breedlove, Jesse L.
              and Prince, Jacob S. and Dowdle, Logan T. and Nau, Matthias and Caron, Brad
              and Pestilli, Franco and Charest, Ian and Hutchinson, J. Benjamin
              and Naselaris, Thomas and Kay, Kendrick},
    year = {2022},
    pages = {116--126},
}
        @Article{Freeman2013,
                author={Freeman, Jeremy
                and Ziemba, Corey M.
                and Heeger, David J.
                and Simoncelli, Eero P.
                and Movshon, J. Anthony},
                title={A functional and perceptual signature of the second visual area in primates},
                journal={Nature Neuroscience},
                year={2013},
                month={Jul},
                day={01},
                volume={16},
                number={7},
                pages={974-981},
                abstract={The authors examined neuronal responses in V1 and V2 to synthetic texture stimuli that replicate higher-order statistical dependencies found in natural images. V2, but not V1, responded differentially to these textures, in both macaque (single neurons) and human (fMRI). Human detection of naturalistic structure in the same images was predicted by V2 responses, suggesting a role for V2 in representing natural image structure.},
                issn={1546-1726},
                doi={10.1038/nn.3402},
                url={https://doi.org/10.1038/nn.3402}
                }
        @article{li2026triplen,
    title = {Triple-N dataset: large-scale fMRI-guided dense recordings of nonhuman
             primate neural responses to natural scenes},
    author = {Li, Yipeng and Liu, Xieyi and Li, Wanru and Yang, Jia and Gong, Baoqi
              and Jin, Wei and Gong, Zhengxin and Wang, Kesheng and Luo, Jingqiu
              and Zhao, Zishuo and Bao, Pinglei},
    journal = {Nature Neuroscience},
    year = {2026},
    doi = {10.1038/s41593-026-02322-z},
    url = {https://doi.org/10.1038/s41593-026-02322-z},
}
        @article {Marques2021.03.01.433495,
	author = {Marques, Tiago and Schrimpf, Martin and DiCarlo, James J.},
	title = {Multi-scale hierarchical neural network models that bridge from single neurons in the primate primary visual cortex to object recognition behavior},
	elocation-id = {2021.03.01.433495},
	year = {2021},
	doi = {10.1101/2021.03.01.433495},
	publisher = {Cold Spring Harbor Laboratory},
	abstract = {Primate visual object recognition relies on the representations in cortical areas at the top of the ventral stream that are computed by a complex, hierarchical network of neural populations. While recent work has created reasonably accurate image-computable hierarchical neural network models of those neural stages, those models do not yet bridge between the properties of individual neurons and the overall emergent behavior of the ventral stream. One reason we cannot yet do this is that individual artificial neurons in multi-stage models have not been shown to be functionally similar to individual biological neurons. Here, we took an important first step by building and evaluating hundreds of hierarchical neural network models in how well their artificial single neurons approximate macaque primary visual cortical (V1) neurons. We found that single neurons in certain models are surprisingly similar to their biological counterparts and that the distributions of single neuron properties, such as those related to orientation and spatial frequency tuning, approximately match those in macaque V1. Critically, we observed that hierarchical models with V1 stages that better match macaque V1 at the single neuron level are also more aligned with human object recognition behavior. Finally, we show that an optimized classical neuroscientific model of V1 is more functionally similar to primate V1 than all of the tested multi-stage models, suggesting room for further model improvements with tangible payoffs in closer alignment to human behavior. These results provide the first multi-stage, multi-scale models that allow our field to ask precisely how the specific properties of individual V1 neurons relate to recognition behavior.HighlightsImage-computable hierarchical neural network models can be naturally extended to create hierarchical {\textquotedblleft}brain models{\textquotedblright} that allow direct comparison with biological neural networks at multiple scales {\textendash} from single neurons, to population of neurons, to behavior.Single neurons in some of these hierarchical brain models are functionally similar to single neurons in macaque primate visual cortex (V1)Some hierarchical brain models have processing stages in which the entire distribution of artificial neuron properties closely matches the biological distributions of those same properties in macaque V1Hierarchical brain models whose V1 processing stages better match the macaque V1 stage also tend to be more aligned with human object recognition behavior at their output stageCompeting Interest StatementThe authors have declared no competing interest.},
	URL = {https://www.biorxiv.org/content/early/2021/08/13/2021.03.01.433495},
	eprint = {https://www.biorxiv.org/content/early/2021/08/13/2021.03.01.433495.full.pdf},
	journal = {bioRxiv}
}
        @article{Cavanaugh2002,
            author = {Cavanaugh, James R. and Bair, Wyeth and Movshon, J. A.},
            doi = {10.1152/jn.00692.2001},
            isbn = {0022-3077 (Print) 0022-3077 (Linking)},
            issn = {0022-3077},
            journal = {Journal of Neurophysiology},
            mendeley-groups = {Benchmark effects/Done,Benchmark effects/*Surround Suppression},
            number = {5},
            pages = {2530--2546},
            pmid = {12424292},
            title = {{Nature and Interaction of Signals From the Receptive Field Center and Surround in Macaque V1 Neurons}},
            url = {http://www.physiology.org/doi/10.1152/jn.00692.2001},
            volume = {88},
            year = {2002}
            }
        @article{Freeman2013,
            author = {Freeman, Jeremy and Ziemba, Corey M. and Heeger, David J. and Simoncelli, E. P. and Movshon, J. A.},
            doi = {10.1038/nn.3402},
            issn = {10976256},
            journal = {Nature Neuroscience},
            number = {7},
            pages = {974--981},
            pmid = {23685719},
            publisher = {Nature Publishing Group},
            title = {{A functional and perceptual signature of the second visual area in primates}},
            url = {http://dx.doi.org/10.1038/nn.3402},
            volume = {16},
            year = {2013}
            }
        @article{Schiller1976,
            author = {Schiller, P. H. and Finlay, B. L. and Volman, S. F.},
            doi = {10.1152/jn.1976.39.6.1352},
            issn = {0022-3077},
            journal = {Journal of neurophysiology},
            number = {6},
            pages = {1334--1351},
            pmid = {825624},
            title = {{Quantitative studies of single-cell properties in monkey striate cortex. III. Spatial Frequency}},
            url = {http://www.ncbi.nlm.nih.gov/pubmed/825624},
            volume = {39},
            year = {1976}
            }
        @article{papale_extensive_2025,
	title = {An extensive dataset of spiking activity to reveal the syntax of the ventral stream},
	volume = {113},
	issn = {08966273},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S089662732400881X},
	doi = {10.1016/j.neuron.2024.12.003},
	journal = {Neuron},
	author = {Papale, Paolo and Wang, Feng and Self, Matthew W. and Roelfsema, Pieter R.},
	year = {2025},
}
        @inproceedings{santurkar2019computer,
    title={Computer Vision with a Single (Robust) Classifier},
    author={Shibani Santurkar and Dimitris Tsipras and Brandon Tran and Andrew Ilyas and Logan Engstrom and Aleksander Madry},
    booktitle={ArXiv preprint arXiv:1906.09453},
    year={2019}
}
        @inproceedings{zerbe_laion-fmri_2026,
      title = {{LAION}-{fMRI}: A densely sampled 7T-fMRI dataset providing broad coverage of natural image diversity},
      author = {Zerbe, Josefine and Roth, Johannes and Mell, Maggie Mae and Herholz, Peer and Knapen, Tomas and Hebart, Martin N.},
      year = {2026},
      booktitle = {Vision Sciences Society Annual Meeting},
  }
        @article{cowley2026compact,
    title={Compact deep neural network models of the visual cortex},
    author={Cowley, Benjamin R and Stan, Patricia L and Pillow, Jonathan W and Smith, Matthew A},
    journal={Nature},
    volume={652},
    number={8111},
    pages={947--954},
    year={2026},
    publisher={Nature Publishing Group},
    doi={10.1038/s41586-026-10150-1},
    url={https://doi.org/10.1038/s41586-026-10150-1}}
        @article{muzellec_reverse_2026,
      title = {Reverse predictivity for bidirectional comparison of neural networks and biological brains},
      volume = {8},
      issn = {2522-5839},
      url = {https://doi.org/10.1038/s42256-026-01204-0},
      doi = {10.1038/s42256-026-01204-0},
      number = {3},
      journal = {Nature Machine Intelligence},
      author = {Muzellec, Sabine and Kar, Kohitij},
      month = mar,
      year = {2026},
      pages = {474--488},
}
        @article {Majaj13402,
            author = {Majaj, Najib J. and Hong, Ha and Solomon, Ethan A. and DiCarlo, James J.},
            title = {Simple Learned Weighted Sums of Inferior Temporal Neuronal Firing Rates Accurately Predict Human Core Object Recognition Performance},
            volume = {35},
            number = {39},
            pages = {13402--13418},
            year = {2015},
            doi = {10.1523/JNEUROSCI.5181-14.2015},
            publisher = {Society for Neuroscience},
            abstract = {To go beyond qualitative models of the biological substrate of object recognition, we ask: can a single ventral stream neuronal linking hypothesis quantitatively account for core object recognition performance over a broad range of tasks? We measured human performance in 64 object recognition tests using thousands of challenging images that explore shape similarity and identity preserving object variation. We then used multielectrode arrays to measure neuronal population responses to those same images in visual areas V4 and inferior temporal (IT) cortex of monkeys and simulated V1 population responses. We tested leading candidate linking hypotheses and control hypotheses, each postulating how ventral stream neuronal responses underlie object recognition behavior. Specifically, for each hypothesis, we computed the predicted performance on the 64 tests and compared it with the measured pattern of human performance. All tested hypotheses based on low- and mid-level visually evoked activity (pixels, V1, and V4) were very poor predictors of the human behavioral pattern. However, simple learned weighted sums of distributed average IT firing rates exactly predicted the behavioral pattern. More elaborate linking hypotheses relying on IT trial-by-trial correlational structure, finer IT temporal codes, or ones that strictly respect the known spatial substructures of IT ({	extquotedblleft}face patches{	extquotedblright}) did not improve predictive power. Although these results do not reject those more elaborate hypotheses, they suggest a simple, sufficient quantitative model: each object recognition task is learned from the spatially distributed mean firing rates (100 ms) of \~{}60,000 IT neurons and is executed as a simple weighted sum of those firing rates.SIGNIFICANCE STATEMENT We sought to go beyond qualitative models of visual object recognition and determine whether a single neuronal linking hypothesis can quantitatively account for core object recognition behavior. To achieve this, we designed a database of images for evaluating object recognition performance. We used multielectrode arrays to characterize hundreds of neurons in the visual ventral stream of nonhuman primates and measured the object recognition performance of \&gt;100 human observers. Remarkably, we found that simple learned weighted sums of firing rates of neurons in monkey inferior temporal (IT) cortex accurately predicted human performance. Although previous work led us to expect that IT would outperform V4, we were surprised by the quantitative precision with which simple IT-based linking hypotheses accounted for human behavior.},
            issn = {0270-6474},
            URL = {https://www.jneurosci.org/content/35/39/13402},
            eprint = {https://www.jneurosci.org/content/35/39/13402.full.pdf},
            journal = {Journal of Neuroscience}}
        @misc{Sanghavi_DiCarlo_2021,
  title={Sanghavi2020},
  url={osf.io/chwdk},
  DOI={10.17605/OSF.IO/CHWDK},
  publisher={OSF},
  author={Sanghavi, Sachi and DiCarlo, James J},
  year={2021},
  month={Nov}
}
        @misc{Sanghavi_Jozwik_DiCarlo_2021,
  title={SanghaviJozwik2020},
  url={osf.io/fhy36},
  DOI={10.17605/OSF.IO/FHY36},
  publisher={OSF},
  author={Sanghavi, Sachi and Jozwik, Kamila M and DiCarlo, James J},
  year={2021},
  month={Nov}
}
        @misc{Sanghavi_Murty_DiCarlo_2021,
  title={SanghaviMurty2020},
  url={osf.io/fchme},
  DOI={10.17605/OSF.IO/FCHME},
  publisher={OSF},
  author={Sanghavi, Sachi and Murty, N A R and DiCarlo, James J},
  year={2021},
  month={Nov}
}
        @article{gifford_large_2022,
	title = {A large and rich {EEG} dataset for modeling human visual object recognition},
	volume = {264},
	issn = {10538119},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1053811922008758},
	doi = {10.1016/j.neuroimage.2022.119754},
	journal = {NeuroImage},
	author = {Gifford, Alessandro T. and Dwivedi, Kshitij and Roig, Gemma and Cichy, Radoslaw M.},
	year = {2022},
}
        @Article{Kar2019,
                                                    author={Kar, Kohitij
                                                    and Kubilius, Jonas
                                                    and Schmidt, Kailyn
                                                    and Issa, Elias B.
                                                    and DiCarlo, James J.},
                                                    title={Evidence that recurrent circuits are critical to the ventral stream's execution of core object recognition behavior},
                                                    journal={Nature Neuroscience},
                                                    year={2019},
                                                    month={Jun},
                                                    day={01},
                                                    volume={22},
                                                    number={6},
                                                    pages={974-983},
                                                    abstract={Non-recurrent deep convolutional neural networks (CNNs) are currently the best at modeling core object recognition, a behavior that is supported by the densely recurrent primate ventral stream, culminating in the inferior temporal (IT) cortex. If recurrence is critical to this behavior, then primates should outperform feedforward-only deep CNNs for images that require additional recurrent processing beyond the feedforward IT response. Here we first used behavioral methods to discover hundreds of these `challenge' images. Second, using large-scale electrophysiology, we observed that behaviorally sufficient object identity solutions emerged {	extasciitilde}30{	hinspace}ms later in the IT cortex for challenge images compared with primate performance-matched `control' images. Third, these behaviorally critical late-phase IT response patterns were poorly predicted by feedforward deep CNN activations. Notably, very-deep CNNs and shallower recurrent CNNs better predicted these late IT responses, suggesting that there is a functional equivalence between additional nonlinear transformations and recurrence. Beyond arguing that recurrent circuits are critical for rapid object identification, our results provide strong constraints for future recurrent model development.},
                                                    issn={1546-1726},
                                                    doi={10.1038/s41593-019-0392-5},
                                                    url={https://doi.org/10.1038/s41593-019-0392-5}
                                                    }
        @article {Rajalingham240614,
                author = {Rajalingham, Rishi and Issa, Elias B. and Bashivan, Pouya and Kar, Kohitij and Schmidt, Kailyn and DiCarlo, James J.},
                title = {Large-scale, high-resolution comparison of the core visual object recognition behavior of humans, monkeys, and state-of-the-art deep artificial neural networks},
                elocation-id = {240614},
                year = {2018},
                doi = {10.1101/240614},
                publisher = {Cold Spring Harbor Laboratory},
                abstract = {Primates{	extemdash}including humans{	extemdash}can typically recognize objects in visual images at a glance even in the face of naturally occurring identity-preserving image transformations (e.g. changes in viewpoint). A primary neuroscience goal is to uncover neuron-level mechanistic models that quantitatively explain this behavior by predicting primate performance for each and every image. Here, we applied this stringent behavioral prediction test to the leading mechanistic models of primate vision (specifically, deep, convolutional, artificial neural networks; ANNs) by directly comparing their behavioral signatures against those of humans and rhesus macaque monkeys. Using high-throughput data collection systems for human and monkey psychophysics, we collected over one million behavioral trials for 2400 images over 276 binary object discrimination tasks. Consistent with previous work, we observed that state-of-the-art deep, feed-forward convolutional ANNs trained for visual categorization (termed DCNNIC models) accurately predicted primate patterns of object-level confusion. However, when we examined behavioral performance for individual images within each object discrimination task, we found that all tested DCNNIC models were significantly non-predictive of primate performance, and that this prediction failure was not accounted for by simple image attributes, nor rescued by simple model modifications. These results show that current DCNNIC models cannot account for the image-level behavioral patterns of primates, and that new ANN models are needed to more precisely capture the neural mechanisms underlying primate object vision. To this end, large-scale, high-resolution primate behavioral benchmarks{	extemdash}such as those obtained here{	extemdash}could serve as direct guides for discovering such models.SIGNIFICANCE STATEMENT Recently, specific feed-forward deep convolutional artificial neural networks (ANNs) models have dramatically advanced our quantitative understanding of the neural mechanisms underlying primate core object recognition. In this work, we tested the limits of those ANNs by systematically comparing the behavioral responses of these models with the behavioral responses of humans and monkeys, at the resolution of individual images. Using these high-resolution metrics, we found that all tested ANN models significantly diverged from primate behavior. Going forward, these high-resolution, large-scale primate behavioral benchmarks could serve as direct guides for discovering better ANN models of the primate visual system.},
                URL = {https://www.biorxiv.org/content/early/2018/02/12/240614},
                eprint = {https://www.biorxiv.org/content/early/2018/02/12/240614.full.pdf},
                journal = {bioRxiv}
            }
        @article{geirhos2021partial,
              title={Partial success in closing the gap between human and machine vision},
              author={Geirhos, Robert and Narayanappa, Kantharaju and Mitzkus, Benjamin and Thieringer, Tizian and Bethge, Matthias and Wichmann, Felix A and Brendel, Wieland},
              journal={Advances in Neural Information Processing Systems},
              volume={34},
              year={2021},
              url={https://openreview.net/forum?id=QkljT4mrfs}
        }
        @article{BAKER2022104913,
                title = {Deep learning models fail to capture the configural nature of human shape perception},
                journal = {iScience},
                volume = {25},
                number = {9},
                pages = {104913},
                year = {2022},
                issn = {2589-0042},
                doi = {https://doi.org/10.1016/j.isci.2022.104913},
                url = {https://www.sciencedirect.com/science/article/pii/S2589004222011853},
                author = {Nicholas Baker and James H. Elder},
                keywords = {Biological sciences, Neuroscience, Sensory neuroscience},
                abstract = {Summary
                A hallmark of human object perception is sensitivity to the holistic configuration of the local shape features of an object. Deep convolutional neural networks (DCNNs) are currently the dominant models for object recognition processing in the visual cortex, but do they capture this configural sensitivity? To answer this question, we employed a dataset of animal silhouettes and created a variant of this dataset that disrupts the configuration of each object while preserving local features. While human performance was impacted by this manipulation, DCNN performance was not, indicating insensitivity to object configuration. Modifications to training and architecture to make networks more brain-like did not lead to configural processing, and none of the networks were able to accurately predict trial-by-trial human object judgements. We speculate that to match human configural sensitivity, networks must be trained to solve a broader range of object tasks beyond category recognition.}
        }
        @misc{ferguson_ngo_lee_dicarlo_schrimpf_2024,
         title={How Well is Visual Search Asymmetry predicted by a Binary-Choice, Rapid, Accuracy-based Visual-search, Oddball-detection (BRAVO) task?},
         url={osf.io/5ba3n},
         DOI={10.17605/OSF.IO/5BA3N},
         publisher={OSF},
         author={Ferguson, Michael E, Jr and Ngo, Jerry and Lee, Michael and DiCarlo, James and Schrimpf, Martin},
         year={2024},
         month={Jun}
}
        @article {Maniquet2024.04.02.587669,
	author = {Maniquet, Tim and de Beeck, Hans Op and Costantino, Andrea Ivan},
	title = {Recurrent issues with deep neural network models of visual recognition},
	elocation-id = {2024.04.02.587669},
	year = {2024},
	doi = {10.1101/2024.04.02.587669},
	publisher = {Cold Spring Harbor Laboratory},
	URL = {https://www.biorxiv.org/content/early/2024/04/10/2024.04.02.587669},
	eprint = {https://www.biorxiv.org/content/early/2024/04/10/2024.04.02.587669.full.pdf},
	journal = {bioRxiv}
}
        @INPROCEEDINGS{5206848,  
                                                author={J. {Deng} and W. {Dong} and R. {Socher} and L. {Li} and  {Kai Li} and  {Li Fei-Fei}},  
                                                booktitle={2009 IEEE Conference on Computer Vision and Pattern Recognition},   
                                                title={ImageNet: A large-scale hierarchical image database},   
                                                year={2009},  
                                                volume={},  
                                                number={},  
                                                pages={248-255},
                                            }
        @ARTICLE{Hendrycks2019-di,
   title         = "Benchmarking Neural Network Robustness to Common Corruptions
                    and Perturbations",
   author        = "Hendrycks, Dan and Dietterich, Thomas",
   abstract      = "In this paper we establish rigorous benchmarks for image
                    classifier robustness. Our first benchmark, ImageNet-C,
                    standardizes and expands the corruption robustness topic,
                    while showing which classifiers are preferable in
                    safety-critical applications. Then we propose a new dataset
                    called ImageNet-P which enables researchers to benchmark a
                    classifier's robustness to common perturbations. Unlike
                    recent robustness research, this benchmark evaluates
                    performance on common corruptions and perturbations not
                    worst-case adversarial perturbations. We find that there are
                    negligible changes in relative corruption robustness from
                    AlexNet classifiers to ResNet classifiers. Afterward we
                    discover ways to enhance corruption and perturbation
                    robustness. We even find that a bypassed adversarial defense
                    provides substantial common perturbation robustness.
                    Together our benchmarks may aid future work toward networks
                    that robustly generalize.",
   month         =  mar,
   year          =  2019,
   archivePrefix = "arXiv",
   primaryClass  = "cs.LG",
   eprint        = "1903.12261",
   url           = "https://arxiv.org/abs/1903.12261"
}
        @article{hermann2020origins,
              title={The origins and prevalence of texture bias in convolutional neural networks},
              author={Hermann, Katherine and Chen, Ting and Kornblith, Simon},
              journal={Advances in Neural Information Processing Systems},
              volume={33},
              pages={19000--19015},
              year={2020},
              url={https://proceedings.neurips.cc/paper/2020/hash/db5f9f42a7157abe65bb145000b5871a-Abstract.html}
        }

Evaluation and I/O

Test datasets: ImageNet-1k validation set
Validation datasets Probable: show confidence source Probable — curation workbook: ImageNet-1k validation set
Input format: RGB 384x384x3, 1000-class logits
Output format: Not documented
Tokenizer: Not documented
Model version Probable: show confidence source Probable — curation workbook: timm library weights

metadata.yaml · Schema v2.0

This annotated template shows the structure of a model’s metadata.yaml. Each section groups related information; comments explain the expected types and allowed values.

Required: schema_version, domain, and models keyed by model identifier. Other fields may be omitted or set to null when undocumented. Use [] for empty lists.

The values below are illustrative, not this model’s metadata. Metadata changes are proposed in repository pull requests and published after merge.

# metadata.yaml — proposed schema v2.0
# Example values below are illustrative, not metadata for a real model.
# Required: schema_version, domain, and models keyed by exact model identifier.
# Other fields may be omitted or set to null when undocumented.
# Use [] for an empty list. Do not use "unknown" as a numeric/boolean value.
# Keep identifiers exact, including checkpoint suffixes.

schema_version: "2.0"  # String; quote the version.

domain: vision  # Must match the repository's registered domain.
models:
  example-model:
    sources:
      example-source:
        kind: other  # paper | huggingface | other | unreviewed
        url: https://example.org/model-card
        citation: Illustrative source, not evidence for a real model.
    model:
      display_name: Example model
      version: null  # String, e.g. "1.0".
      architecture:
        family: convolutional_neural_network  # String describing the architecture family.
        description: A convolutional model trained for image classification.
      parameter_count: 25000000  # Nonnegative integer; count, not "25M".
      parameter_count_exact: false  # Boolean; false means the count is approximate.
      trainable_layers: "All layers"  # Text; can describe partial fine-tuning.
      recurrent: false  # Boolean.
      input_resolution:
        channels: 3  # Nonnegative integer.
        height: 224  # Nonnegative integer, pixels.
        width: 224  # Nonnegative integer, pixels.
      visual_degrees: null  # Nonnegative number; vision models only.
      visual_degrees_description: null  # Text explaining the field of view.
      supervision:
        type: supervised  # String, e.g. supervised, self_supervised, weakly_supervised.
        description: Trained using class labels.

    training:
      process: null  # Text describing the training procedure.
      objective: null  # Text describing what the model learns.
      loss: null  # Text, e.g. "Cross-entropy".
      learning_rate: null  # Text; supports schedules, e.g. "0.1 with cosine decay".
      batch_size: null  # Text; supports different values across training stages.
      preprocessing: null  # Text describing normalization and augmentation.

    data:
      summary: null  # Text summarizing the data used.
      training_datasets:
        - identifier: example-training-set  # Optional dataset identifier.
          name: Example training set  # Required for each dataset entry.
          role: training  # training | pretraining | fine_tuning
          description: null  # Text describing this dataset's use.

    eval:
      test_datasets: []  # Entries: {identifier: optional, name: required, description: optional}.
      validation_datasets: []  # Same entry structure; role is implied by the list.

    io:
      modality: image  # String, e.g. image or text.
      interface: null  # Text describing the model's interface.
      input_format: null  # Text describing accepted inputs and their shape.
      output_format: null  # Text describing returned values and their shape.
      tokenizer: null  # Text; language models, where applicable.

    provenance:
      weights_provider: null  # Organization or repository providing the weights.
      checkpoint: null  # Exact checkpoint identifier.
      source_url: null  # Link to the original code or model card.
      curation_confidence: null  # Text summarizing confidence in the curated record.

    legal:
      license: null  # License identifier or full terms; distinguish code and weights.

    people:
      creators: []  # List of names, e.g. ["Example Researcher"].
      organizations: []  # List of organization names.

    use:
      applications: []  # List of intended applications (strings).
      users: []  # List of intended user groups (strings).
      limitations: []  # List of known limitations (strings).
      biases: []  # List of known biases (strings).

    lineage:
      base_models:
        - identifier: example-base  # Optional; exact identifier in the same domain.
          name: Example base model  # Required for each base-model entry.
          relationship: fine_tuned_from  # variant_of | fine_tuned_from | derived_from

    # Optional verification records. Omit this section if no verification is recorded.
    # Paths refer to fields in this YAML document, not database columns.
    assertions:
      - path: /model/architecture
        status: probable  # verified | probable | uncertain | undocumented
        sources: [example-source]  # References the structured sources above.

Region	Layer
V1	`stages.2.blocks.1`
V2	`stages.2.blocks.13.conv_dw`
V4	`stages.2.blocks.1`
IT	`stages.2.blocks.12.conv_dw`