Scores on benchmarks
Model rank shown below is with respect to all public models..300 |
average_vision
rank 129
81 benchmarks |
|
.301 |
neural_vision
rank 133
38 benchmarks |
|
.332 |
V1
rank 209
24 benchmarks |
|
.035 |
Coggan2024_fMRI.V1-rdm
v1
rank 103
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.706 |
Marques2020
[reference]
rank 174
22 benchmarks |
|
.945 |
V1-orientation
rank 5
7 benchmarks |
|
.998 |
Marques2020_Ringach2002-or_selective
v1
rank 36
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.935 |
Marques2020_Ringach2002-circular_variance
v1
rank 25
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.918 |
Marques2020_Ringach2002-orth_pref_ratio
v1
rank 37
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.926 |
Marques2020_Ringach2002-cv_bandwidth_ratio
v1
rank 40
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.884 |
Marques2020_DeValois1982-pref_or
v1
rank 269
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.972 |
Marques2020_Ringach2002-opr_cv_diff
v1
rank 19
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.981 |
Marques2020_Ringach2002-or_bandwidth
v1
rank 4
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.688 |
V1-spatial_frequency
rank 274
3 benchmarks |
|
.537 |
Marques2020_DeValois1982-peak_sf
v1
rank 281
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.723 |
Marques2020_Schiller1976-sf_bandwidth
v1
[reference]
rank 255
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.804 |
Marques2020_Schiller1976-sf_selective
v1
[reference]
rank 221
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.653 |
V1-response_selectivity
rank 193
4 benchmarks |
|
.857 |
Marques2020_FreemanZiemba2013-texture_selectivity
v1
[reference]
rank 35
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.271 |
Marques2020_Ringach2002-modulation_ratio
v1
rank 322
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.715 |
Marques2020_FreemanZiemba2013-texture_variance_ratio
v1
[reference]
rank 182
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.769 |
Marques2020_FreemanZiemba2013-texture_sparseness
v1
[reference]
rank 110
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.641 |
V1-receptive_field_size
rank 146
2 benchmarks |
|
.849 |
Marques2020_Cavanaugh2002-grating_summation_field
v1
[reference]
rank 54
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.433 |
Marques2020_Cavanaugh2002-surround_diameter
v1
[reference]
rank 199
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.607 |
V1-surround_modulation
rank 189
1 benchmark |
|
.607 |
Marques2020_Cavanaugh2002-surround_suppression_index
v1
[reference]
rank 189
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.584 |
V1-texture_modulation
rank 218
2 benchmarks |
|
.508 |
Marques2020_FreemanZiemba2013-abs_texture_modulation_index
v1
[reference]
rank 182
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.659 |
Marques2020_FreemanZiemba2013-texture_modulation_index
v1
[reference]
rank 261
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.827 |
V1-response_magnitude
rank 229
3 benchmarks |
|
.856 |
Marques2020_FreemanZiemba2013-max_texture
v1
[reference]
rank 178
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.892 |
Marques2020_Ringach2002-max_dc
v1
rank 285
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.733 |
Marques2020_FreemanZiemba2013-max_noise
v1
[reference]
rank 238
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.256 |
FreemanZiemba2013.V1-pls
v2
[reference]
rank 247
|
|
recordings from
102
sites in
V1
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.170 |
V2
rank 143
2 benchmarks |
|
.014 |
Coggan2024_fMRI.V2-rdm
v1
rank 149
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.327 |
FreemanZiemba2013.V2-pls
v2
[reference]
rank 83
|
|
recordings from
103
sites in
V2
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.357 |
V4
rank 266
5 benchmarks |
|
.023 |
Coggan2024_fMRI.V4-rdm
v1
rank 105
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.455 |
SanghaviJozwik2020.V4-pls
v1
[reference]
rank 227
|
|
recordings from
50
sites in
V4
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.609 |
Sanghavi2020.V4-pls
v1
[reference]
rank 236
|
|
recordings from
47
sites in
V4
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.162 |
SanghaviMurty2020.V4-pls
v1
[reference]
rank 321
|
|
recordings from
46
sites in
V4
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.536 |
MajajHong2015.V4-pls
v3
[reference]
rank 328
|
|
recordings from
88
sites in
V4
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.345 |
IT
rank 88
7 benchmarks |
|
.349 |
Bracci2019.anteriorVTC-rdm
v1
rank 36
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.131 |
Coggan2024_fMRI.IT-rdm
v1
rank 136
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.340 |
SanghaviMurty2020.IT-pls
v1
[reference]
rank 228
|
|
recordings from
29
sites in
IT
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.546 |
Sanghavi2020.IT-pls
v1
[reference]
rank 40
|
|
recordings from
88
sites in
IT
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.509 |
SanghaviJozwik2020.IT-pls
v1
[reference]
rank 115
|
|
recordings from
26
sites in
IT
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.543 |
MajajHong2015.IT-pls
v3
[reference]
rank 67
|
|
recordings from
168
sites in
IT
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
X |
Kar2019-ost
v2
[reference]
rank X
|
|
recordings from
424
sites in
IT
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.299 |
behavior_vision
rank 126
43 benchmarks |
|
.471 |
Rajalingham2018-i2n
v2
[reference]
rank 205
|
|
match-to-sample task
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.274 |
Geirhos2021-error_consistency
[reference]
rank 94
17 benchmarks |
|
.510 |
Geirhos2021colour-error_consistency
v1
[reference]
rank 68
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.166 |
Geirhos2021contrast-error_consistency
v1
[reference]
rank 129
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.228 |
Geirhos2021cueconflict-error_consistency
v1
[reference]
rank 95
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.138 |
Geirhos2021edge-error_consistency
v1
[reference]
rank 63
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.453 |
Geirhos2021eidolonI-error_consistency
v1
[reference]
rank 79
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.534 |
Geirhos2021eidolonII-error_consistency
v1
[reference]
rank 53
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.473 |
Geirhos2021eidolonIII-error_consistency
v1
[reference]
rank 48
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.336 |
Geirhos2021falsecolour-error_consistency
v1
[reference]
rank 108
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.043 |
Geirhos2021highpass-error_consistency
v1
[reference]
rank 188
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.185 |
Geirhos2021lowpass-error_consistency
v1
[reference]
rank 105
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.111 |
Geirhos2021phasescrambling-error_consistency
v1
[reference]
rank 135
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.114 |
Geirhos2021powerequalisation-error_consistency
v1
[reference]
rank 124
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.143 |
Geirhos2021rotation-error_consistency
v1
[reference]
rank 120
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.449 |
Geirhos2021silhouette-error_consistency
v1
[reference]
rank 127
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.125 |
Geirhos2021sketch-error_consistency
v1
[reference]
rank 90
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.392 |
Geirhos2021stylized-error_consistency
v1
[reference]
rank 73
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.254 |
Geirhos2021uniformnoise-error_consistency
v1
[reference]
rank 83
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.392 |
Maniquet2024
rank 159
2 benchmarks |
|
.277 |
Maniquet2024-confusion_similarity
v1
[reference]
rank 152
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.507 |
Maniquet2024-tasks_consistency
v1
[reference]
rank 148
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.529 |
Ferguson2024
[reference]
rank 50
14 benchmarks |
|
.798 |
Ferguson2024half-value_delta
v1
[reference]
rank 45
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.104 |
Ferguson2024gray_hard-value_delta
v1
[reference]
rank 189
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.532 |
Ferguson2024lle-value_delta
v1
[reference]
rank 80
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.041 |
Ferguson2024juncture-value_delta
v1
[reference]
rank 155
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
1.0 |
Ferguson2024color-value_delta
v1
[reference]
rank 1
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.905 |
Ferguson2024round_v-value_delta
v1
[reference]
rank 38
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.296 |
Ferguson2024eighth-value_delta
v1
[reference]
rank 63
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.621 |
Ferguson2024quarter-value_delta
v1
[reference]
rank 53
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.177 |
Ferguson2024convergence-value_delta
v1
[reference]
rank 169
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.092 |
Ferguson2024round_f-value_delta
v1
[reference]
rank 179
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
1.0 |
Ferguson2024llh-value_delta
v1
[reference]
rank 1
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
1.0 |
Ferguson2024circle_line-value_delta
v1
[reference]
rank 1
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.177 |
Ferguson2024gray_easy-value_delta
v1
[reference]
rank 130
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.657 |
Ferguson2024tilted_line-value_delta
v1
[reference]
rank 77
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.176 |
Hebart2023-match
v1
rank 150
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.551 |
Coggan2024_behavior-ConditionWiseAccuracySimilarity
v1
rank 31
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.526 |
engineering_vision
rank 9
25 benchmarks |
|
.726 |
ImageNet-top1
v1
[reference]
rank 90
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.521 |
ImageNet-C-top1
[reference]
rank 29
4 benchmarks |
|
.511 |
ImageNet-C-noise-top1
v2
[reference]
rank 42
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.456 |
ImageNet-C-blur-top1
v2
[reference]
rank 24
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.540 |
ImageNet-C-weather-top1
v2
[reference]
rank 37
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.575 |
ImageNet-C-digital-top1
v2
[reference]
rank 32
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.285 |
ObjectNet-top1
v1
[reference]
rank 16
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.639 |
Geirhos2021-top1
[reference]
rank 45
17 benchmarks |
|
.977 |
Geirhos2021colour-top1
v1
[reference]
rank 79
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.830 |
Geirhos2021contrast-top1
v1
[reference]
rank 101
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.383 |
Geirhos2021cueconflict-top1
v1
[reference]
rank 22
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.362 |
Geirhos2021edge-top1
v1
[reference]
rank 51
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.524 |
Geirhos2021eidolonI-top1
v1
[reference]
rank 83
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.577 |
Geirhos2021eidolonII-top1
v1
[reference]
rank 43
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.627 |
Geirhos2021eidolonIII-top1
v1
[reference]
rank 34
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.975 |
Geirhos2021falsecolour-top1
v1
[reference]
rank 39
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.388 |
Geirhos2021highpass-top1
v1
[reference]
rank 120
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.477 |
Geirhos2021lowpass-top1
v1
[reference]
rank 65
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.653 |
Geirhos2021phasescrambling-top1
v1
[reference]
rank 72
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.820 |
Geirhos2021powerequalisation-top1
v1
[reference]
rank 59
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.742 |
Geirhos2021rotation-top1
v1
[reference]
rank 64
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.537 |
Geirhos2021silhouette-top1
v1
[reference]
rank 87
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.731 |
Geirhos2021sketch-top1
v1
[reference]
rank 37
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.594 |
Geirhos2021stylized-top1
v1
[reference]
rank 22
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.674 |
Geirhos2021uniformnoise-top1
v1
[reference]
rank 29
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.459 |
Hermann2020
[reference]
rank 20
2 benchmarks |
|
.353 |
Hermann2020cueconflict-shape_match
v1
[reference]
rank 23
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
.565 |
Hermann2020cueconflict-shape_bias
v1
[reference]
rank 25
|
|
![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
How to use
from brainscore_vision import load_model model = load_model("efficientnet-b7") model.start_task(...) model.start_recording(...) model.look_at(...)
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 {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{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{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{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, 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} } @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_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_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 {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 \>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}} @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 {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} } @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} } @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" } @inproceedings{DBLP:conf/nips/BarbuMALWGTK19, author = {Andrei Barbu and David Mayo and Julian Alverio and William Luo and Christopher Wang and Dan Gutfreund and Josh Tenenbaum and Boris Katz}, title = {ObjectNet: {A} large-scale bias-controlled dataset for pushing the limits of object recognition models}, booktitle = {NeurIPS 2019}, pages = {9448--9458}, year = {2019}, url = {https://proceedings.neurips.cc/paper/2019/hash/97af07a14cacba681feacf3012730892-Abstract.html}, } @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} }