Scores on benchmarks

Model rank shown below is with respect to all public models.
.142 average_vision rank 346
81 benchmarks
.142
0
ceiling
best
median
.223 neural_vision rank 332
38 benchmarks
.223
0
ceiling
best
median
.105 V1 rank 345
24 benchmarks
.105
0
ceiling
best
median
.316 FreemanZiemba2013.V1-pls v2 [reference] rank 45
.316
0
ceiling
best
median
recordings from 102 sites in V1
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.176 V2 rank 117
2 benchmarks
.176
0
ceiling
best
median
.353 FreemanZiemba2013.V2-pls v2 [reference] rank 22
.353
0
ceiling
best
median
recordings from 103 sites in V2
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.355 V4 rank 272
5 benchmarks
.355
0
ceiling
best
median
.438 SanghaviJozwik2020.V4-pls v1 [reference] rank 269
.438
0
ceiling
best
median
recordings from 50 sites in V4
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.617 Sanghavi2020.V4-pls v1 [reference] rank 198
.617
0
ceiling
best
median
recordings from 47 sites in V4
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.170 SanghaviMurty2020.V4-pls v1 [reference] rank 290
.170
0
ceiling
best
median
recordings from 46 sites in V4
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.550 MajajHong2015.V4-pls v3 [reference] rank 287
.550
0
ceiling
best
median
recordings from 88 sites in V4
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.255 IT rank 285
7 benchmarks
.255
0
ceiling
best
median
.313 SanghaviMurty2020.IT-pls v1 [reference] rank 277
.313
0
ceiling
best
median
recordings from 29 sites in IT
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.496 Sanghavi2020.IT-pls v1 [reference] rank 258
.496
0
ceiling
best
median
recordings from 88 sites in IT
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.471 SanghaviJozwik2020.IT-pls v1 [reference] rank 221
.471
0
ceiling
best
median
recordings from 26 sites in IT
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.508 MajajHong2015.IT-pls v3 [reference] rank 204
.508
0
ceiling
best
median
recordings from 168 sites in IT
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
X Kar2019-ost v2 [reference] rank X
X
0
ceiling
best
median
recordings from 424 sites in IT
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.060 behavior_vision rank 314
43 benchmarks
.060
0
ceiling
best
median
.370 Rajalingham2018-i2n v2 [reference] rank 280
.370
0
ceiling
best
median
match-to-sample task
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.114 Geirhos2021-error_consistency [reference] rank 199
17 benchmarks
.114
0
ceiling
best
median
.134 Geirhos2021colour-error_consistency v1 [reference] rank 205
.134
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.123 Geirhos2021contrast-error_consistency v1 [reference] rank 163
.123
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.128 Geirhos2021cueconflict-error_consistency v1 [reference] rank 216
.128
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.069 Geirhos2021edge-error_consistency v1 [reference] rank 183
.069
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.281 Geirhos2021eidolonI-error_consistency v1 [reference] rank 161
.281
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.252 Geirhos2021eidolonII-error_consistency v1 [reference] rank 176
.252
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.167 Geirhos2021eidolonIII-error_consistency v1 [reference] rank 205
.167
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.055 Geirhos2021falsecolour-error_consistency v1 [reference] rank 227
.055
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.045 Geirhos2021highpass-error_consistency v1 [reference] rank 173
.045
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.056 Geirhos2021lowpass-error_consistency v1 [reference] rank 238
.056
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.060 Geirhos2021phasescrambling-error_consistency v1 [reference] rank 191
.060
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.097 Geirhos2021powerequalisation-error_consistency v1 [reference] rank 139
.097
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.049 Geirhos2021rotation-error_consistency v1 [reference] rank 242
.049
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.203 Geirhos2021silhouette-error_consistency v1 [reference] rank 211
.203
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.041 Geirhos2021sketch-error_consistency v1 [reference] rank 227
.041
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.139 Geirhos2021stylized-error_consistency v1 [reference] rank 191
.139
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.038 Geirhos2021uniformnoise-error_consistency v1 [reference] rank 225
.038
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.295 engineering_vision rank 190
25 benchmarks
.295
0
ceiling
best
median
.577 ImageNet-top1 v1 [reference] rank 189
.577
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.202 ImageNet-C-top1 [reference] rank 174
4 benchmarks
.202
0
ceiling
best
median
.099 ImageNet-C-noise-top1 v2 [reference] rank 202
.099
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.190 ImageNet-C-blur-top1 v2 [reference] rank 172
.190
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.229 ImageNet-C-weather-top1 v2 [reference] rank 175
.229
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.291 ImageNet-C-digital-top1 v2 [reference] rank 172
.291
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.069 ObjectNet-top1 v1 [reference] rank 111
.069
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.434 Geirhos2021-top1 [reference] rank 216
17 benchmarks
.434
0
ceiling
best
median
.864 Geirhos2021colour-top1 v1 [reference] rank 211
.864
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.435 Geirhos2021contrast-top1 v1 [reference] rank 208
.435
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.189 Geirhos2021cueconflict-top1 v1 [reference] rank 175
.189
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.294 Geirhos2021edge-top1 v1 [reference] rank 104
.294
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.474 Geirhos2021eidolonI-top1 v1 [reference] rank 174
.474
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.448 Geirhos2021eidolonII-top1 v1 [reference] rank 211
.448
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.438 Geirhos2021eidolonIII-top1 v1 [reference] rank 211
.438
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.777 Geirhos2021falsecolour-top1 v1 [reference] rank 222
.777
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.264 Geirhos2021highpass-top1 v1 [reference] rank 198
.264
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.345 Geirhos2021lowpass-top1 v1 [reference] rank 192
.345
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.520 Geirhos2021phasescrambling-top1 v1 [reference] rank 194
.520
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.505 Geirhos2021powerequalisation-top1 v1 [reference] rank 205
.505
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.482 Geirhos2021rotation-top1 v1 [reference] rank 220
.482
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.431 Geirhos2021silhouette-top1 v1 [reference] rank 177
.431
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.450 Geirhos2021sketch-top1 v1 [reference] rank 223
.450
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.279 Geirhos2021stylized-top1 v1 [reference] rank 227
.279
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.177 Geirhos2021uniformnoise-top1 v1 [reference] rank 234
.177
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.195 Hermann2020 [reference] rank 190
2 benchmarks
.195
0
ceiling
best
median
.151 Hermann2020cueconflict-shape_match v1 [reference] rank 173
.151
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9
.239 Hermann2020cueconflict-shape_bias v1 [reference] rank 186
.239
0
ceiling
best
median
sample 0 sample 1 sample 2 sample 3 sample 4 sample 5 sample 6 sample 7 sample 8 sample 9

How to use

from brainscore_vision import load_model
model = load_model("alexnet")
model.start_task(...)
model.start_recording(...)
model.look_at(...)

Benchmarks bibtex

@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}
        }
        @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}
        }
        

Layer Commitment

No layer commitments found for this model. Older submissions might not have stored this information but will be updated when evaluated on new benchmarks.

Visual Angle

8 degrees