Scores on benchmarks
Model rank shown below is with respect to all public models.| .072 |
average_vision
rank 415
99 benchmarks |
|
| .006 |
neural_vision
rank 499
56 benchmarks |
|
| .025 |
V1
rank 483
28 benchmarks |
|
| .178 |
Coggan2024_fMRI.V1-rdm
v1
rank 38
|
|
|
24 images 
|
||
| .138 |
behavior_vision
rank 264
43 benchmarks |
|
| .098 |
Geirhos2021-error_consistency
[reference]
rank 239
17 benchmarks |
|
| .179 |
Geirhos2021colour-error_consistency
v1
[reference]
rank 212
|
|
|
640 images 
|
||
| .079 |
Geirhos2021contrast-error_consistency
v1
[reference]
rank 246
|
|
|
800 images 
|
||
| .160 |
Geirhos2021cueconflict-error_consistency
v1
[reference]
rank 183
|
|
|
1280 images 
|
||
| .084 |
Geirhos2021edge-error_consistency
v1
[reference]
rank 150
|
|
|
160 images 
|
||
| .077 |
Geirhos2021eidolonI-error_consistency
v1
[reference]
rank 296
|
|
|
800 images 
|
||
| .173 |
Geirhos2021eidolonII-error_consistency
v1
[reference]
rank 236
|
|
|
640 images 
|
||
| .123 |
Geirhos2021eidolonIII-error_consistency
v1
[reference]
rank 257
|
|
|
480 images 
|
||
| .218 |
Geirhos2021falsecolour-error_consistency
v1
[reference]
rank 191
|
|
|
560 images 
|
||
| .048 |
Geirhos2021highpass-error_consistency
v1
[reference]
rank 197
|
|
|
640 images 
|
||
| .090 |
Geirhos2021lowpass-error_consistency
v1
[reference]
rank 221
|
|
|
800 images 
|
||
| .051 |
Geirhos2021phasescrambling-error_consistency
v1
[reference]
rank 237
|
|
|
640 images 
|
||
| .013 |
Geirhos2021powerequalisation-error_consistency
v1
[reference]
rank 302
|
|
|
560 images 
|
||
| .063 |
Geirhos2021rotation-error_consistency
v1
[reference]
rank 229
|
|
|
960 images 
|
||
| .052 |
Geirhos2021silhouette-error_consistency
v1
[reference]
rank 309
|
|
|
160 images 
|
||
| .044 |
Geirhos2021sketch-error_consistency
v1
[reference]
rank 246
|
|
|
800 images 
|
||
| .159 |
Geirhos2021stylized-error_consistency
v1
[reference]
rank 206
|
|
|
800 images 
|
||
| .061 |
Geirhos2021uniformnoise-error_consistency
v1
[reference]
rank 215
|
|
|
800 images 
|
||
| .091 |
Baker2022
rank 182
3 benchmarks |
|
| .274 |
Baker2022fragmented-accuracy_delta
v1
[reference]
rank 133
|
|
|
716 images 
|
||
| .000 |
Baker2022frankenstein-accuracy_delta
v1
[reference]
rank 172
|
|
|
716 images 
|
||
| .000 |
Baker2022inverted-accuracy_delta
v1
[reference]
rank 62
|
|
|
360 images 
|
||
| .146 |
BMD2024
rank 145
4 benchmarks |
|
| .166 |
BMD2024.dotted_1Behavioral-accuracy_distance
v1
rank 94
|
|
|
100 images 
|
||
| .126 |
BMD2024.dotted_2Behavioral-accuracy_distance
v1
rank 127
|
|
|
100 images 
|
||
| .134 |
BMD2024.texture_1Behavioral-accuracy_distance
v1
rank 151
|
|
|
100 images 
|
||
| .157 |
BMD2024.texture_2Behavioral-accuracy_distance
v1
rank 137
|
|
|
100 images 
|
||
| .019 |
Ferguson2024
[reference]
rank 283
14 benchmarks |
|
| .270 |
Ferguson2024gray_hard-value_delta
v1
[reference]
rank 197
|
|
|
2_way_afc task
48 images 
|
||
| .233 |
Hebart2023-match
v1
rank 171
|
|
|
1854 images 
|
||
| .417 |
Maniquet2024
rank 224
2 benchmarks |
|
| .164 |
Maniquet2024-confusion_similarity
v1
[reference]
rank 257
|
|
|
13600 images 
|
||
| .671 |
Maniquet2024-tasks_consistency
v1
[reference]
rank 102
|
|
|
13600 images 
|
||
| .095 |
Coggan2024_behavior-ConditionWiseAccuracySimilarity
v1
rank 200
|
|
|
22560 images 
|
||
| .104 |
engineering_vision
rank 303
25 benchmarks |
|
| .520 |
Geirhos2021-top1
[reference]
rank 179
17 benchmarks |
|
| .948 |
Geirhos2021colour-top1
v1
[reference]
rank 174
|
|
|
640 images 
|
||
| .855 |
Geirhos2021contrast-top1
v1
[reference]
rank 117
|
|
|
800 images 
|
||
| .158 |
Geirhos2021cueconflict-top1
v1
[reference]
rank 260
|
|
|
1280 images 
|
||
| .194 |
Geirhos2021edge-top1
v1
[reference]
rank 227
|
|
|
160 images 
|
||
| .498 |
Geirhos2021eidolonI-top1
v1
[reference]
rank 157
|
|
|
800 images 
|
||
| .511 |
Geirhos2021eidolonII-top1
v1
[reference]
rank 167
|
|
|
640 images 
|
||
| .498 |
Geirhos2021eidolonIII-top1
v1
[reference]
rank 187
|
|
|
480 images 
|
||
| .929 |
Geirhos2021falsecolour-top1
v1
[reference]
rank 156
|
|
|
560 images 
|
||
| .500 |
Geirhos2021highpass-top1
v1
[reference]
rank 80
|
|
|
640 images 
|
||
| .419 |
Geirhos2021lowpass-top1
v1
[reference]
rank 158
|
|
|
800 images 
|
||
| .539 |
Geirhos2021phasescrambling-top1
v1
[reference]
rank 215
|
|
|
640 images 
|
||
| .598 |
Geirhos2021powerequalisation-top1
v1
[reference]
rank 206
|
|
|
560 images 
|
||
| .674 |
Geirhos2021rotation-top1
v1
[reference]
rank 148
|
|
|
960 images 
|
||
| .319 |
Geirhos2021silhouette-top1
v1
[reference]
rank 259
|
|
|
160 images 
|
||
| .488 |
Geirhos2021sketch-top1
v1
[reference]
rank 239
|
|
|
800 images 
|
||
| .329 |
Geirhos2021stylized-top1
v1
[reference]
rank 233
|
|
|
800 images 
|
||
| .381 |
Geirhos2021uniformnoise-top1
v1
[reference]
rank 177
|
|
|
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.
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}
}