Leaderboard Explore Compare Profile Community Blog FAQ Competition 2024 Report Issue

Scores on benchmarks

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

.330	average_vision rank 84 111 benchmarks	.330 0 ceiling best median

.274	neural_vision rank 98 68 benchmarks	.274 0 ceiling best median

.297	V1 rank 98 31 benchmarks	.297 0 ceiling best median

.358	Allen2022_fmri_surface.V1 rank 36 2 benchmarks	.358 0 ceiling best median

.223	Allen2022_fmri_surface.V1-rdm v1 [reference] rank 41	.223 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.494	Allen2022_fmri_surface.V1-ridge v1 [reference] rank 28	.494 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.220	FreemanZiemba2013.V1-pls v3 [reference] rank 310	.220 0 ceiling best median
	recordings from 102 sites in V1 315 images Sample stimuli cannot be displayed publicly for this benchmark.

.614	Hebart2023_fmri.V1-ridgecv v3 rank 24	.614 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.675	Marques2020 [reference] rank 314 22 benchmarks	.675 0 ceiling best median

.862	V1-orientation rank 197 7 benchmarks	.862 0 ceiling best median

.961	Marques2020_DeValois1982-pref_or v1 rank 157	.961 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.762	Marques2020_Ringach2002-circular_variance v1 rank 266	.762 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.921	Marques2020_Ringach2002-cv_bandwidth_ratio v1 rank 52	.921 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.932	Marques2020_Ringach2002-opr_cv_diff v1 rank 84	.932 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.845	Marques2020_Ringach2002-or_bandwidth v1 rank 210	.845 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.875	Marques2020_Ringach2002-or_selective v1 rank 298	.875 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.742	Marques2020_Ringach2002-orth_pref_ratio v1 rank 260	.742 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.297	V1-receptive_field_size rank 365 2 benchmarks	.297 0 ceiling best median

.595	Marques2020_Cavanaugh2002-surround_diameter v1 [reference] rank 163	.595 0 ceiling best median
	2304 images Sample stimuli cannot be displayed publicly for this benchmark.

.951	V1-response_magnitude rank 22 3 benchmarks	.951 0 ceiling best median

.960	Marques2020_FreemanZiemba2013-max_noise v1 [reference] rank 11	.960 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.952	Marques2020_FreemanZiemba2013-max_texture v1 [reference] rank 55	.952 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.942	Marques2020_Ringach2002-max_dc v1 rank 220	.942 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.574	V1-response_selectivity rank 341 4 benchmarks	.574 0 ceiling best median

.944	Marques2020_FreemanZiemba2013-texture_selectivity v1 [reference] rank 5	.944 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.573	Marques2020_FreemanZiemba2013-texture_variance_ratio v1 [reference] rank 349	.573 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.779	Marques2020_Ringach2002-modulation_ratio v1 rank 30	.779 0 ceiling best median
	1152 images Sample stimuli cannot be displayed publicly for this benchmark.

.489	V1-spatial_frequency rank 393 3 benchmarks	.489 0 ceiling best median

.312	Marques2020_DeValois1982-peak_sf v1 rank 396	.312 0 ceiling best median
	2112 images Sample stimuli cannot be displayed publicly for this benchmark.

.851	Marques2020_Schiller1976-sf_bandwidth v1 [reference] rank 192	.851 0 ceiling best median
	2112 images Sample stimuli cannot be displayed publicly for this benchmark.

.306	Marques2020_Schiller1976-sf_selective v1 [reference] rank 405	.306 0 ceiling best median
	2112 images Sample stimuli cannot be displayed publicly for this benchmark.

.888	V1-surround_modulation rank 4 1 benchmark	.888 0 ceiling best median

.888	Marques2020_Cavanaugh2002-surround_suppression_index v1 [reference] rank 4	.888 0 ceiling best median
	2304 images Sample stimuli cannot be displayed publicly for this benchmark.

.665	V1-texture_modulation rank 151 2 benchmarks	.665 0 ceiling best median

.566	Marques2020_FreemanZiemba2013-abs_texture_modulation_index v1 [reference] rank 162	.566 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.764	Marques2020_FreemanZiemba2013-texture_modulation_index v1 [reference] rank 115	.764 0 ceiling best median
	450 images Sample stimuli cannot be displayed publicly for this benchmark.

.034	Coggan2024_fMRI.V1-rdm v1 rank 170	.034 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.174	Zerbe2026_fmri.V1 rank 104 3 benchmarks	.174 0 ceiling best median

.336	Zerbe2026_fmri.V1-ood-ridgecv v1 rank 71	.336 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.186	Zerbe2026_fmri.V1-rdm-pearson v1 rank 60	.186 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.314	V2 rank 56 8 benchmarks	.314 0 ceiling best median

.393	Allen2022_fmri_surface.V2 rank 10 2 benchmarks	.393 0 ceiling best median

.266	Allen2022_fmri_surface.V2-rdm v1 [reference] rank 34	.266 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.520	Allen2022_fmri_surface.V2-ridge v1 [reference] rank 3	.520 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.250	FreemanZiemba2013.V2-pls v3 [reference] rank 221	.250 0 ceiling best median
	recordings from 103 sites in V2 315 images Sample stimuli cannot be displayed publicly for this benchmark.

.631	Hebart2023_fmri.V2-ridgecv v3 rank 9	.631 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.062	Coggan2024_fMRI.V2-rdm v1 rank 148	.062 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.231	Zerbe2026_fmri.V2 rank 97 3 benchmarks	.231 0 ceiling best median

.257	Zerbe2026_fmri.V2-rdm-pearson v1 rank 22	.257 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.438	Zerbe2026_fmri.V2-tau-ridgecv v1 rank 8	.438 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.285	V4 rank 93 13 benchmarks	.285 0 ceiling best median

.345	Allen2022_fmri_surface.V4 rank 14 2 benchmarks	.345 0 ceiling best median

.217	Allen2022_fmri_surface.V4-rdm v1 [reference] rank 38	.217 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.472	Allen2022_fmri_surface.V4-ridge v1 [reference] rank 5	.472 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.385	Hebart2023_fmri.V4-ridgecv v3 rank 3	.385 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.508	MajajHong2015.V4-pls v4 [reference] rank 267	.508 0 ceiling best median
	recordings from 88 sites in V4 2560 images Sample stimuli cannot be displayed publicly for this benchmark.

.562	Sanghavi2020.V4-pls v2 [reference] rank 158	.562 0 ceiling best median
	recordings from 47 sites in V4 5760 images Sample stimuli cannot be displayed publicly for this benchmark.

.477	SanghaviJozwik2020.V4-pls v2 [reference] rank 89	.477 0 ceiling best median
	recordings from 50 sites in V4 4916 images Sample stimuli cannot be displayed publicly for this benchmark.

.209	SanghaviMurty2020.V4-pls v2 [reference] rank 171	.209 0 ceiling best median
	recordings from 46 sites in V4 300 images Sample stimuli cannot be displayed publicly for this benchmark.

.038	Coggan2024_fMRI.V4-rdm v1 rank 114	.038 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.324	Zerbe2026_fmri.V4 rank 14 3 benchmarks	.324 0 ceiling best median

.415	Zerbe2026_fmri.V4-ood-ridgecv v1 rank 16	.415 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.189	Zerbe2026_fmri.V4-rdm-pearson v1 rank 35	.189 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.368	Zerbe2026_fmri.V4-tau-ridgecv v1 rank 8	.368 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.201	IT rank 126 16 benchmarks	.201 0 ceiling best median

.400	Allen2022_fmri_surface.IT rank 43 2 benchmarks	.400 0 ceiling best median

.261	Allen2022_fmri_surface.IT-rdm v1 [reference] rank 74	.261 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.539	Allen2022_fmri_surface.IT-ridge v1 [reference] rank 20	.539 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.206	Bracci2019.anteriorVTC-rdm v1 rank 195	.206 0 ceiling best median
	27 images Sample stimuli cannot be displayed publicly for this benchmark.

.341	Hebart2023_fmri.IT-ridgecv v3 rank 10	.341 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.385	MajajHong2015.IT-pls v4 [reference] rank 331	.385 0 ceiling best median
	recordings from 168 sites in IT 2560 images Sample stimuli cannot be displayed publicly for this benchmark.

.038	MajajHong2015public.IT-reverse_pls v4 [reference] rank 95	.038 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.409	SanghaviJozwik2020.IT-pls v2 [reference] rank 245	.409 0 ceiling best median
	recordings from 26 sites in IT 4916 images Sample stimuli cannot be displayed publicly for this benchmark.

.302	SanghaviMurty2020.IT-pls v2 [reference] rank 255	.302 0 ceiling best median
	recordings from 29 sites in IT 300 images Sample stimuli cannot be displayed publicly for this benchmark.

.360	Coggan2024_fMRI.IT-rdm v1 rank 133	.360 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.176	Zerbe2026_fmri.IT rank 94 3 benchmarks	.176 0 ceiling best median

.227	Zerbe2026_fmri.IT-ood-ridgecv v1 rank 27	.227 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.300	Zerbe2026_fmri.IT-tau-ridgecv v1 rank 42	.300 0 ceiling best median
	Sample stimuli cannot be displayed publicly for this benchmark.

.387	behavior_vision rank 92 43 benchmarks	.387 0 ceiling best median

.491	Geirhos2021-error_consistency [reference] rank 45 17 benchmarks	.491 0 ceiling best median

.202	Geirhos2021colour-error_consistency v1 [reference] rank 208	.202 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.073	Geirhos2021contrast-error_consistency v1 [reference] rank 253	.073 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.846	Geirhos2021cueconflict-error_consistency v1 [reference] rank 8	.846 0 ceiling best median
	1280 images Sample stimuli cannot be displayed publicly for this benchmark.

.705	Geirhos2021edge-error_consistency v1 [reference] rank 20	.705 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.436	Geirhos2021eidolonI-error_consistency v1 [reference] rank 107	.436 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.408	Geirhos2021eidolonII-error_consistency v1 [reference] rank 120	.408 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.359	Geirhos2021eidolonIII-error_consistency v1 [reference] rank 120	.359 0 ceiling best median
	480 images Sample stimuli cannot be displayed publicly for this benchmark.

.339	Geirhos2021falsecolour-error_consistency v1 [reference] rank 125	.339 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.353	Geirhos2021highpass-error_consistency v1 [reference] rank 38	.353 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.370	Geirhos2021lowpass-error_consistency v1 [reference] rank 70	.370 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.508	Geirhos2021phasescrambling-error_consistency v1 [reference] rank 30	.508 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.487	Geirhos2021powerequalisation-error_consistency v1 [reference] rank 38	.487 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.475	Geirhos2021rotation-error_consistency v1 [reference] rank 30	.475 0 ceiling best median
	960 images Sample stimuli cannot be displayed publicly for this benchmark.

.901	Geirhos2021silhouette-error_consistency v1 [reference] rank 27	.901 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.666	Geirhos2021sketch-error_consistency v1 [reference] rank 16	.666 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.755	Geirhos2021stylized-error_consistency v1 [reference] rank 10	.755 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.472	Geirhos2021uniformnoise-error_consistency v1 [reference] rank 64	.472 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.631	Baker2022 rank 35 3 benchmarks	.631 0 ceiling best median

.691	Baker2022fragmented-accuracy_delta v1 [reference] rank 79	.691 0 ceiling best median
	716 images Sample stimuli cannot be displayed publicly for this benchmark.

.220	Baker2022frankenstein-accuracy_delta v1 [reference] rank 147	.220 0 ceiling best median
	716 images Sample stimuli cannot be displayed publicly for this benchmark.

.982	Baker2022inverted-accuracy_delta v1 [reference] rank 19	.982 0 ceiling best median
	360 images Sample stimuli cannot be displayed publicly for this benchmark.

.513	BMD2024 rank 20 4 benchmarks	.513 0 ceiling best median

.551	BMD2024.dotted_1Behavioral-accuracy_distance v1 rank 19	.551 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.304	BMD2024.dotted_2Behavioral-accuracy_distance v1 rank 21	.304 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.620	BMD2024.texture_1Behavioral-accuracy_distance v1 rank 20	.620 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.577	BMD2024.texture_2Behavioral-accuracy_distance v1 rank 19	.577 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.669	Ferguson2024 [reference] rank 12 14 benchmarks	.669 0 ceiling best median

.320	Ferguson2024circle_line-value_delta v1 [reference] rank 141	.320 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.

.385	Ferguson2024convergence-value_delta v1 [reference] rank 136	.385 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

1.0	Ferguson2024eighth-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.

.845	Ferguson2024gray_easy-value_delta v1 [reference] rank 26	.845 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.942	Ferguson2024gray_hard-value_delta v1 [reference] rank 28	.942 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.653	Ferguson2024half-value_delta v1 [reference] rank 104	.653 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.184	Ferguson2024juncture-value_delta v1 [reference] rank 122	.184 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.125	Ferguson2024lle-value_delta v1 [reference] rank 248	.125 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

1.0	Ferguson2024llh-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.

.706	Ferguson2024quarter-value_delta v1 [reference] rank 52	.706 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.544	Ferguson2024round_f-value_delta v1 [reference] rank 92	.544 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

1.0	Ferguson2024round_v-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.

.657	Ferguson2024tilted_line-value_delta v1 [reference] rank 111	.657 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.528	Hebart2023-match v1 rank 6	.528 0 ceiling best median
	1854 images Sample stimuli cannot be displayed publicly for this benchmark.

.261	Coggan2024_behavior-ConditionWiseAccuracySimilarity v1 rank 133	.261 0 ceiling best median
	22560 images Sample stimuli cannot be displayed publicly for this benchmark.

.212	engineering_vision rank 258 25 benchmarks	.212 0 ceiling best median

.827	Geirhos2021-top1 [reference] rank 7 17 benchmarks	.827 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.

.999	Geirhos2021contrast-top1 v1 [reference] rank 2	.999 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.500	Geirhos2021cueconflict-top1 v1 [reference] rank 14	.500 0 ceiling best median
	1280 images Sample stimuli cannot be displayed publicly for this benchmark.

.825	Geirhos2021edge-top1 v1 [reference] rank 21	.825 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.564	Geirhos2021eidolonI-top1 v1 [reference] rank 48	.564 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.672	Geirhos2021eidolonII-top1 v1 [reference] rank 8	.672 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.754	Geirhos2021eidolonIII-top1 v1 [reference] rank 6	.754 0 ceiling best median
	480 images Sample stimuli cannot be displayed publicly for this benchmark.

.996	Geirhos2021falsecolour-top1 v1 [reference] rank 3	.996 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.995	Geirhos2021highpass-top1 v1 [reference] rank 1	.995 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.708	Geirhos2021lowpass-top1 v1 [reference] rank 7	.708 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.933	Geirhos2021phasescrambling-top1 v1 [reference] rank 4	.933 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.989	Geirhos2021powerequalisation-top1 v1 [reference] rank 4	.989 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.975	Geirhos2021rotation-top1 v1 [reference] rank 8	.975 0 ceiling best median
	960 images Sample stimuli cannot be displayed publicly for this benchmark.

.713	Geirhos2021silhouette-top1 v1 [reference] rank 11	.713 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.905	Geirhos2021sketch-top1 v1 [reference] rank 22	.905 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.664	Geirhos2021stylized-top1 v1 [reference] rank 16	.664 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.874	Geirhos2021uniformnoise-top1 v1 [reference] rank 2	.874 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.235	Hermann2020 [reference] rank 150 2 benchmarks	.235 0 ceiling best median

.470	Hermann2020cueconflict-shape_match v1 [reference] rank 14	.470 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("dinov2_vitl14_lc_res336")
model.start_task(...)
model.start_recording(...)
model.look_at(...)

Model API

Code examples

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.

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 {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}
            }
        @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}
}
        @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{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{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{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{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}
        }

Layer Commitment

Region	Layer
V1	backbone.blocks.7
V2	backbone.blocks.11
V4	backbone.blocks.11
IT	backbone.blocks.15

Visual Angle

None degrees