Scores on benchmarks
Model rank shown below is with respect to all public models.| .072 |
average_vision
rank 417
120 benchmarks |
|
| .006 |
neural_vision
rank 506
77 benchmarks |
|
| .022 |
V1
rank 491
33 benchmarks |
|
| .178 |
Coggan2024_fMRI.V1-rdm
v1
rank 42
|
|
|
24 images 
|
||
| .138 |
behavior_vision
rank 267
43 benchmarks |
|
| .098 |
Geirhos2021-error_consistency
[reference]
rank 245
17 benchmarks |
|
| .179 |
Geirhos2021colour-error_consistency
v1
[reference]
rank 217
|
|
|
640 images 
|
||
| .079 |
Geirhos2021contrast-error_consistency
v1
[reference]
rank 252
|
|
|
800 images 
|
||
| .160 |
Geirhos2021cueconflict-error_consistency
v1
[reference]
rank 190
|
|
|
1280 images 
|
||
| .084 |
Geirhos2021edge-error_consistency
v1
[reference]
rank 158
|
|
|
160 images 
|
||
| .077 |
Geirhos2021eidolonI-error_consistency
v1
[reference]
rank 301
|
|
|
800 images 
|
||
| .173 |
Geirhos2021eidolonII-error_consistency
v1
[reference]
rank 245
|
|
|
640 images 
|
||
| .123 |
Geirhos2021eidolonIII-error_consistency
v1
[reference]
rank 264
|
|
|
480 images 
|
||
| .218 |
Geirhos2021falsecolour-error_consistency
v1
[reference]
rank 199
|
|
|
560 images 
|
||
| .048 |
Geirhos2021highpass-error_consistency
v1
[reference]
rank 200
|
|
|
640 images 
|
||
| .090 |
Geirhos2021lowpass-error_consistency
v1
[reference]
rank 227
|
|
|
800 images 
|
||
| .051 |
Geirhos2021phasescrambling-error_consistency
v1
[reference]
rank 244
|
|
|
640 images 
|
||
| .013 |
Geirhos2021powerequalisation-error_consistency
v1
[reference]
rank 307
|
|
|
560 images 
|
||
| .063 |
Geirhos2021rotation-error_consistency
v1
[reference]
rank 237
|
|
|
960 images 
|
||
| .052 |
Geirhos2021silhouette-error_consistency
v1
[reference]
rank 314
|
|
|
160 images 
|
||
| .044 |
Geirhos2021sketch-error_consistency
v1
[reference]
rank 252
|
|
|
800 images 
|
||
| .159 |
Geirhos2021stylized-error_consistency
v1
[reference]
rank 213
|
|
|
800 images 
|
||
| .061 |
Geirhos2021uniformnoise-error_consistency
v1
[reference]
rank 220
|
|
|
800 images 
|
||
| .091 |
Baker2022
rank 189
3 benchmarks |
|
| .274 |
Baker2022fragmented-accuracy_delta
v1
[reference]
rank 145
|
|
|
716 images 
|
||
| .000 |
Baker2022frankenstein-accuracy_delta
v1
[reference]
rank 179
|
|
|
716 images 
|
||
| .000 |
Baker2022inverted-accuracy_delta
v1
[reference]
rank 71
|
|
|
360 images 
|
||
| .146 |
BMD2024
rank 155
4 benchmarks |
|
| .166 |
BMD2024.dotted_1Behavioral-accuracy_distance
v1
rank 103
|
|
|
100 images 
|
||
| .126 |
BMD2024.dotted_2Behavioral-accuracy_distance
v1
rank 135
|
|
|
100 images 
|
||
| .134 |
BMD2024.texture_1Behavioral-accuracy_distance
v1
rank 160
|
|
|
100 images 
|
||
| .157 |
BMD2024.texture_2Behavioral-accuracy_distance
v1
rank 146
|
|
|
100 images 
|
||
| .019 |
Ferguson2024
[reference]
rank 301
14 benchmarks |
|
| .270 |
Ferguson2024gray_hard-value_delta
v1
[reference]
rank 216
|
|
|
2_way_afc task
48 images 
|
||
| .233 |
Hebart2023-match
v1
rank 178
|
|
|
1854 images 
|
||
| .417 |
Maniquet2024
rank 235
2 benchmarks |
|
| .164 |
Maniquet2024-confusion_similarity
v1
[reference]
rank 270
|
|
|
13600 images 
|
||
| .671 |
Maniquet2024-tasks_consistency
v1
[reference]
rank 99
|
|
|
13600 images 
|
||
| .095 |
Coggan2024_behavior-ConditionWiseAccuracySimilarity
v1
rank 209
|
|
|
22560 images 
|
||
| .104 |
engineering_vision
rank 309
25 benchmarks |
|
| .520 |
Geirhos2021-top1
[reference]
rank 184
17 benchmarks |
|
| .948 |
Geirhos2021colour-top1
v1
[reference]
rank 179
|
|
|
640 images 
|
||
| .855 |
Geirhos2021contrast-top1
v1
[reference]
rank 122
|
|
|
800 images 
|
||
| .158 |
Geirhos2021cueconflict-top1
v1
[reference]
rank 266
|
|
|
1280 images 
|
||
| .194 |
Geirhos2021edge-top1
v1
[reference]
rank 232
|
|
|
160 images 
|
||
| .498 |
Geirhos2021eidolonI-top1
v1
[reference]
rank 164
|
|
|
800 images 
|
||
| .511 |
Geirhos2021eidolonII-top1
v1
[reference]
rank 172
|
|
|
640 images 
|
||
| .498 |
Geirhos2021eidolonIII-top1
v1
[reference]
rank 192
|
|
|
480 images 
|
||
| .929 |
Geirhos2021falsecolour-top1
v1
[reference]
rank 161
|
|
|
560 images 
|
||
| .500 |
Geirhos2021highpass-top1
v1
[reference]
rank 90
|
|
|
640 images 
|
||
| .419 |
Geirhos2021lowpass-top1
v1
[reference]
rank 163
|
|
|
800 images 
|
||
| .539 |
Geirhos2021phasescrambling-top1
v1
[reference]
rank 221
|
|
|
640 images 
|
||
| .598 |
Geirhos2021powerequalisation-top1
v1
[reference]
rank 213
|
|
|
560 images 
|
||
| .674 |
Geirhos2021rotation-top1
v1
[reference]
rank 153
|
|
|
960 images 
|
||
| .319 |
Geirhos2021silhouette-top1
v1
[reference]
rank 265
|
|
|
160 images 
|
||
| .488 |
Geirhos2021sketch-top1
v1
[reference]
rank 246
|
|
|
800 images 
|
||
| .329 |
Geirhos2021stylized-top1
v1
[reference]
rank 240
|
|
|
800 images 
|
||
| .381 |
Geirhos2021uniformnoise-top1
v1
[reference]
rank 182
|
|
|
800 images 
|
||
How to use
from brainscore_vision import load_model
model = load_model("resnet50_eMMCR_Vanilla")
model.start_task(...)
model.start_recording(...)
model.look_at(...)
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
@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{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}
}