CoChat
Sign Up
Cited by 204Visual perception and processing mechanismsFace Recognition and PerceptionAdvanced Neural Network Applications

Deep problems with neural network models of human vision

Open access
Bowers, Jeffrey S., Malhotra, Gaurav, Dujmović, Marin, Llera Montero, Milton, Tsvetkov, Christian, Biscione, Valerio, Puebla, Guillermo, Adolfi, Federico +5 more·2023·Behavioral and Brain Sciences
DOI 10.1017/s0140525x22002813
Open this paper in CoChat — free accountOpen PDF

Abstract

Deep neural networks (DNNs) have had extraordinary successes in classifying photographic images of objects and are often described as the best models of biological vision. This conclusion is largely based on three sets of findings: (1) DNNs are more accurate than any other model in classifying images taken from various datasets, (2) DNNs do the best job in predicting the pattern of human errors in classifying objects taken from various behavioral datasets, and (3) DNNs do the best job in predicting brain signals in response to images taken from various brain datasets (e.g., single cell responses or fMRI data). However, these behavioral and brain datasets do not test hypotheses regarding what features are contributing to good predictions and we show that the predictions may be mediated by DNNs that share little overlap with biological vision. More problematically, we show that DNNs account for almost no results from psychological research. This contradicts the common claim that DNNs are good, let alone the best, models of human object recognition. We argue that theorists interested in developing biologically plausible models of human vision need to direct their attention to explaining psychological findings. More generally, theorists need to build models that explain the results of experiments that manipulate independent variables designed to test hypotheses rather than compete on making the best predictions. We conclude by briefly summarizing various promising modeling approaches that focus on psychological data.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1017/s0140525x22002813

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • DCNNs trained to classify objects are more sensitive to local shapes and textures than to global shapes, and tend to ignore relations between parts of objects.

    “Bowers et al. (2022) and Quilty-Dunn et al. (2022) both cite evidence that DCNNs trained to classify objects are more sensitive to local shapes and textures than to global shapes, and tend to ignore relations between parts of objects, suggesting that they do not employ representations of integrated scenes.”

    From Consciousness in Artificial Intelligence: Insights from the Science of Consciousness (2023) · cites this paper as Bowers et al. 2022

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 160

  1. Adolfi, F., Bowers, J. S., & Poeppel, D. (2022). Successes and critical failures of neural networks in capturing human-like speech recognition. arXiv preprint arXiv:2204.03740. · arXiv
  2. Alcorn, M. A., Li, Q., Gong, Z., Wang, C., Mai, L., Ku, W. S., & Nguyen, A. (2019). Strike (with) a pose: Neural networks are easily fooled by strange poses of familiar objects. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4845-4854).
  3. Alexander, D. M., & Van Leeuwen, C. (2010). Mapping of contextual modulation in the population response of primary visual cortex. Cognitive Neurodynamics, 4(1), 1-24.
  4. Ba, J., Mnih, V., & Kavukcuoglu, K. (2014). Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755. · arXiv
  5. Baker, N., Kellman, P.J., Erlikhman, G., & Lu, H. (2018). Deep convolutional networks do not perceive illusory contours. In Proceedings of the 40th Annual conference of the cognitive science society, cognitive science society, Austin, TX (pp. 1310-1315).
  6. Baker, N., Lu, H., Erlikhman, G., & Kellman, P. J. (2018). Deep convolutional networks do not classify based on global object shape. PLoS Computational Biology, 14(12), e1006613.
  7. Barrett, D., Hill, F., Santoro, A., Morcos, A., & Lillicrap, T. (2018, July). Measuring abstract reasoning in neural networks. In International conference on machine learning (pp. 511-520). https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  8. Bhattasali, N. X., Tomov, M., & Gershman, S. (2021, June). CCNLab: A Benchmarking Framework for Computational Cognitive Neuroscience. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).
  9. Biederman, I. (1987). Recognition-by-components: a theory of human image understanding. Psychological Review, 94(2), 115-147.
  10. Biederman, I., & Ju, G. (1988). Surface versus edge-based determinants of visual recognition. Cognitive Psychology, 20(1), 38-64.
  11. Biscione, V., & Bowers, J. S. (2021). Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be. Journal of Machine Learning Research, 22, 1-28.
  12. Biscione, V., & Bowers, J. S. (2022). Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training. Neural Networks, 150, 222-236. https://doi.org/10.1016/j.neunet.2022.02.017. · DOI
  13. Biscione, V., & Bowers, J. S. (2022). Do DNNs trained on natural images acquire gestalt properties?. arXiv preprint arXiv:2203.07302. · arXiv
  14. Blything, R., Biscione, V., & Bowers, J. (2020). A case for robust translation tolerance in humans and CNNs. A commentary on Han et al. arXiv preprint arXiv:2012.05950. · arXiv
  15. Blything, R., Biscione, V., Vankov, I. I., Ludwig, C. J. H., & Bowers, J. S. (2021). The human visual system and CNNs can both support robust online translation tolerance following extreme displacements. Journal of Vision, 21(2):9, 1-16. https://doi.org/10.1167/jov.21.2.9. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press · DOI
  16. Bowers, J. S., & Davis, C. J. (2012b). Is that what Bayesians believe? Reply to Griffiths, Chater, Norris, and Pouget (2012). Psychological Bulletin, 138, 423-426. DOI: 10.1037/a0027750 · DOI · Paper page
  17. Bowers, J.S. & Jones, K.W. (2007). Detecting objects is easier than categorizing them. Quarterly Journal of Experimental Psychology, 61, 552-557.
  18. Bowers, J. S., Vankov, I. I., & Ludwig, C. J. (2016). The visual system supports online translation invariance for object identification. Psychonomic Bulletin & Review, 23, 432-438.
  19. Burgess, C. P., et al. (2019). Monet: Unsupervised scene decomposition and representation. arXiv preprint arXiv:1901.11390. · arXiv
  20. Cadieu, C. F., Hong, H., Yamins, D. L., Pinto, N., Ardila, D., Solomon, E. A., ... & DiCarlo, J. J. (2014). Deep neural networks rival the representation of primate IT cortex for core visual object recognition. PLoS Computational Biology, 10(12), e1003963.
  21. Cao, Y., Grossberg, S., & Markowitz, J. (2011). How does the brain rapidly learn and reorganize view- invariant and position-invariant object representations in the inferotemporal cortex? Neural Networks, 24(10), 1050-1061. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  22. Carpenter, G. A., & Grossberg, S. (1981). Adaptation and transmitter gating in vertebrate photoreceptors. Journal of Theoretical Neurobiology, 1(1), 1-42.
  23. Caucheteux, C., Gramfort, A., & King, J. R. (2022). Deep language algorithms predict semantic comprehension from brain activity. Scientific Reports, 12(1), 1-10.
  24. Cavanagh, P., Hénaff, M. A., Michel, F., Landis, T., Troscianko, T., & Intriligator, J. (1998). Complete sparing of high-contrast color input to motion perception in cortical color blindness. Nature Neuroscience, 1(3), 242-247.
  25. Clune, J., Mouret, J. B., & Lipson, H. (2013). The evolutionary origins of modularity. Proceedings of the Royal Society b: Biological Sciences, 280(1755), 20122863.
  26. Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological measurement, 20(1), 37-46.
  27. Crosby, M., Beyret, B., & Halina, M. (2019). The animal-ai olympics. Nature Machine Intelligence, 1(5), 257-257. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  28. Dapello, J., Marques, T., Schrimpf, M., Geiger, F., Cox, D., & DiCarlo, J. J. (2020). Simulating a primary visual cortex at the front of CNNs improves robustness to image perturbations. Advances in Neural Information Processing Systems, 33, 13073-13087.
  29. Doumas, L. A. A., Puebla, G., Martin, A. E., & Hummel, J. E. (2022). A theory of relation learning and cross-domain generalization. Psychological Review. Advance online publication. https://doi.org/10.1037/rev0000346 · DOI
  30. Driver, J., & Baylis, G. C. (1996). Edge-assignment and figure-ground segmentation in short-term visual matching. Cognitive Psychology, 31(3), 248-306.
  31. Duan, S., Matthey, L., Saraiva, A., Watters, N., Burgess, C. P., Lerchner, A., & Higgins, I. (2019). Unsupervised model selection for variational disentangled representation learning. arXiv preprint arXiv:1905.12614. · arXiv
  32. Dujmović, M., Bowers, J.S., Adolfi, F., & Malhotra, G. (2022). The pitfalls of measuring representational similarity using representational similarity analysis. arXiv preprint https://www.biorxiv.org/content/10.1101/2022.04.05.487135v1 Dujmović, M., Malhotra, G., & Bowers, J. S. (2020). What do adversarial images tell us about human vision? Elife, 9, e55978. · DOI
  33. Duncan, J., & Humphreys, G. W. (1989). Visual search and stimulus similarity. Psychological Review, 96(3), 433-458. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  34. Elmoznino, E., & Bonner, M. F. (2022). High-performing neural network models of visual cortex benefit from high latent dimensionality. bioRxiv.
  35. Erdogan, G., & Jacobs, R. A. (2017). Visual shape perception as Bayesian inference of 3D object-centered shape representations. Psychological Review, 124(6), 740-761.
  36. Evans, B. D., Malhotra, G., & Bowers, J. S. (2022). Biological convolutions improve DNN robustness to noise and generalisation. Neural Networks, 148, 96-110. https://doi.org/10.1016/j.neunet.2021.12.005 · DOI
  37. Farah, M. J. (2004). Visual agnosia. MIT press.
  38. Feather, J., Durango, A., Gonzalez, R., & McDermott, J. (2019). Metamers of neural networks reveal divergence from human perceptual systems. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d\textquotesingle Alché-Buc, E. Fox, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 32 (pp. 10078-10089).
  39. Francis, G., Manassi, M., & Herzog, M. H. (2017). Neural dynamics of grouping and segmentation explain properties of visual crowding. Psychological Review, 124(4), 483-504.
  40. Funke, C. M., Borowski, J., Stosio, K., Brendel, W., Wallis, T. S., & Bethge, M. (2021). Five https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press points to check when comparing visual perception in humans and machines. Journal of Vision, 21(3):16, 1-23.
  41. Garrigan, P., & Kellman, P. J. (2008). Perceptual learning depends on perceptual constancy. Proceedings of the National Academy of Sciences, 105(6), 2248-2253.
  42. Gauthier, I., & Tarr, M. J. (2016). Visual object recognition: Do we (finally) know more now than we did? Annual Review of Vision Science, 2, 377-396.
  43. Geirhos, R., Meding, K., & Wichmann, F. A. (2020). Beyond accuracy: Quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency. arXiv preprint arXiv:2006.16736. · arXiv
  44. Geirhos, R., Narayanappa, K., Mitzkus, B., Thieringer, T., Bethge, M., Wichmann, F. A., & Brendel, W. (2021). Partial success in closing the gap between human and machine vision. arXiv preprint arXiv:2106.07411. · arXiv
  45. Geirhos, R., Temme, C. R., Rauber, J., Schütt, H. H., Bethge, M., & Wichmann, F. A. (2018). Generalisation in humans and deep neural networks. In Advances in Neural Information Processing Systems (pp. 7538-7550). https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  46. Goodale, M. A., & Milner, A. D. (1992). Separate visual pathways for perception and action. Trends in Neurosciences, 15(1), 20-25.
  47. Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwińska, A., ... & Hassabis, D. (2016). Hybrid computing using a neural network with dynamic external memory. Nature, 538(7626), 471-476.
  48. Greff, K., et al.. (2019, May). Multi-object representation learning with iterative variational inference. In International Conference on Machine Learning (pp. 2424-2433).
  49. Greff, K., van Steenkiste, S., & Schmidhuber, J. (2020). On the binding problem in artificial neural networks. arXiv preprint arXiv:2012.05208. · arXiv
  50. Grill-Spector, K., & Kanwisher, N. (2005). Visual recognition: As soon as you know it is there, you know what it is. Psychological Science, 16(2), 152-160.
  51. Grossberg, S. (1980). How does a brain build a cognitive code? Psychological Review, 87, 1-51. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  52. Grossberg, S. (2021). Conscious Mind, Resonant Brain: How Each Brain Makes a Mind. Oxford University Press.
  53. Grossberg, S., & Mingolla, E. (1985). Neural dynamics of form perception: boundary completion, illusory figures, and neon color spreading. Psychological Review, 92(2), 173-211.
  54. Grossberg, S., & Mingolla, E. (1987). Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations. In The adaptive brain II (pp. 143-210). Elsevier.
  55. Guest, O., & Martin, A. E. (2021). On logical inference over brains, behaviour, and artificial neural networks. arXiv preprint psyarxiv.com/tbmcg, doi:10.31234/osf.io/tbmcg · DOI
  56. Gulordava, K., Bojanowski, P., Grave, E., Linzen, T., & Baroni, M. (2018, June). Colorless green recurrent networks dream hierarchically. In Proceedings of NAACL 2018 (pp. 1195- 1205). New Orleans, Louisiana: ACL.
  57. Hacker, C., & Biederman, I. (2018). The invariance of recognition to the stretching of faces is not explained by familiarity or warping to an average face. arXiv preprint https://doi.org/10.31234/osf.io/e5hgx https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press · DOI
  58. Hannagan, T., Agrawal, A., Cohen, L., & Dehaene, S. (2021). Emergence of a compositional neural code for written words: Recycling of a convolutional neural network for reading. Proceedings of the National Academy of Sciences, 118(46).
  59. Hermann, K. L., Chen, T., & Kornblith, S. (2019). The origins and prevalence of texture bias in convolutional neural networks. arXiv preprint arXiv:1911.09071. · arXiv
  60. Hochberg, J., & Brooks, V. (1962). Pictorial recognition as an unlearned ability: A study of one child's performance. The American Journal of Psychology, 75(4), 624-628.
  61. In E. Dietrich & A. Markman (Eds.), Cognitive dynamics: Conceptual change in humans and machines. (pp. 229-264). Cambridge, MA: MIT Press.
  62. Huber, L. S., Geirhos, R., & Wichmann, F. A. (2022). The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks. arXiv preprint arXiv:2205.10144. · arXiv
  63. Hummel, J. E. (2000). Where view-based theories break down: The role of structure in shape perception and object recognition. In E. Deitrich & A. Markman (Eds.), Cognitive dynamics: Conceptual change in humans and machines (pp. 157-185). Mahwah, NJ: Erlbaum https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  64. Hummel, J.E. (2013). Object recognition. In D. Reisburg (ed.), Oxford Handbook of Cognitive Psychology, pp. 32-46. Oxford: Oxford University Press.
  65. Izhikevich E. M. (2004) Which model to use for cortical spiking neurons? IEEE Transactions on Neural Networks Volume 15 Issue 5 September 2004 pp 1063-1070 https://doi.org/10.1109/TNN.2004.832719 · DOI
  66. Jacob, G., Pramod, R. T., Katti, H., & Arun, S. P. (2021). Qualitative similarities and differences in visual object representations between brains and deep networks. Nature Communications, 12(1), 1-14.
  67. Khaligh-Razavi, S. M., & Kriegeskorte, N. (2014). Deep supervised, but not unsupervised, models may explain IT cortical representation. PLoS Computational Biology, 10(11), e1003915.
  68. Kheradpisheh, S. R., Ghodrati, M., Ganjtabesh, M., & Masquelier, T. (2016). Deep networks can resemble human feed-forward vision in invariant object recognition. Scientific Reports, 6(1), 1-24.
  69. Kiani R, Esteky H, Mirpour K, Tanaka K (2007) Object Category Structure in Response Patterns of Neuronal Population in Monkey Inferior Temporal Cortex. Journal of Neurophysiology, 97, 4296-4309. doi:10.1152/jn.00024.2007 https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press · DOI
  70. Kim, J., Linsley, D., Thakkar, K., & Serre, T. (2019). Disentangling neural mechanisms for perceptual grouping. arXiv preprint arXiv:1906.01558. · arXiv
  71. Kriegeskorte, N. (2015). Deep neural networks: a new framework for modeling biological vision and brain information processing. Annual Review of Vision Science, 1, 417-446.
  72. Kriegeskorte, N., Mur, M., Ruff, D. A., Kiani, R., Bodurka, J., Esteky, H., ... & Bandettini, P. A. (2008). Matching categorical object representations in inferior temporal cortex of man and monkey. Neuron, 60(6), 1126-1141.
  73. Kubilius, J., Bracci, S., & Op de Beeck, H. P. (2016). Deep neural networks as a computational model for human shape sensitivity. PLoS Computational Biology, 12(4), e1004896.
  74. Kubilius, J., Schrimpf, M., Kar, K., Hong, H., Majaj, N. J., Rajalingham, R., ... & DiCarlo, J. J. (2019). Brain-like object recognition with high-performing shallow recurrent ANNs. arXiv preprint arXiv:1909.06161. · arXiv
  75. Lehky, S. R., & Sejnowski, T. J. (1988). Network model of shape-from-shading: neural function arises from both receptive and projective fields. Nature, 333(6172), 452-454. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  76. Lehman, J., & Stanley, K. O. (2011). Abandoning objectives: Evolution through the search for novelty alone. Evolutionary Computation, 19(2), 189-223.
  77. Lotter, W., Kreiman, G., & Cox, D. (2020). A neural network trained for prediction mimics diverse features of biological neurons and perception. Nature Machine Intelligence, 2(4), 210-219.
  78. Lissauer, SH. (1890). Ein Fall von Seelenblindheit nebst einem Beitrage zur Theorie derselben. Archiv für Psychiatrie und Nervenkrankheiten, 21(2), 222-270.
  79. Lonnqvist, B., Bornet, A., Doerig, A., & Herzog, M. H. (2021). A comparative biology approach to DNN modeling of vision: A focus on differences, not similarities. Journal of Vision, 21(10), 17-17. doi:https://doi.org/10.1167/jov.21.10.17 · DOI
  80. Mack, M. L., Gauthier, I., Sadr, J., & Palmeri, T. J. (2008). Object detection and basic-level categorization: Sometimes you know it is there before you know what it is. Psychonomic Bulletin & Review, 15(1), 28-35.
  81. Majaj, N. J., Hong, H., Solomon, E. A., & DiCarlo, J. J. (2015). Simple learned weighted sums of inferior temporal neuronal firing rates accurately predict human core object recognition performance. Journal of Neuroscience, 35(39), 13402-13418. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  82. Malhotra, G., Dujmovic, M., & Bowers, J. S. (2022). Feature blindness: a challenge for understanding and modelling visual object recognition. PLOS Computational Biology, 18, e1009572. https://doi.org/10.1101/2021.10.20.465074 · DOI
  83. Malhotra, G., Dujmovic, M., Hummel, J., & Bowers, J. S. (2021). The contrasting shape representations that support object recognition in humans and CNNs. arXiv preprint https://doi.org/10.1101/2021.12.14.472546 · DOI
  84. Marcus, G. F. (1998). Rethinking eliminative connectionism. Cognitive Psychology, 37(3), 243-282.
  85. Marcus, G. (2020). The next decade in ai: four steps towards robust artificial intelligence. arXiv preprint arXiv:2002.06177. · arXiv
  86. Marques, T., Schrimpf, M., & DiCarlo, J. J. (2021). Multi-scale hierarchical neural network models that bridge from single neurons in the primate primary visual cortex to object recognition behavior. arXiv preprint https://doi.org/10.1101/2021.03.01.433495 · DOI
  87. Mayo, D. G. (2018). Statistical inference as severe testing. Cambridge: Cambridge University Press. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  88. McClelland, J. L., Rumelhart, D. E., & PDP Research Group. (1986). Parallel Distributed Processing (Vol. 2). Cambridge, MA: MIT press.
  89. Mehrer, J., Spoerer, C. J., Jones, E. C., Kriegeskorte, N., & Kietzmann, T. C. (2021). An ecologically motivated image dataset for deep learning yields better models of human vision. Proceedings of the National Academy of Sciences, 118(8).
  90. Messina, N., Amato, G., Carrara, F., Gennaro, C., & Falchi, F. (2021). Solving the same- different task with convolutional neural networks. Pattern Recognition Letters, 143, 75-80.
  91. Millet, J., & King, J.-R. (2021). Inductive biases, pretraining and fine-tuning jointly account for brain responses to speech. ArXiv:2103.01032 [ · arXiv
  92. Miozzo, M., & Caramazza, A. (1998). Varieties of pure alexia: The case of failure to access graphemic representations. Cognitive Neuropsychology, 15(1-2), 203-238.
  93. Mitchell, J., & Bowers, J. (2020, December). Priorless Recurrent Networks Learn Curiously. In Proceedings of the 28th International Conference on Computational Linguistics (pp. 5147-5158).
  94. Mitchell, J., & Bowers, J. S. (2021). Generalisation in Neural Networks Does not Require Feature Overlap. arXiv preprint arXiv:2107.06872. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press · arXiv
  95. Mnih, V., Heess, N., & Graves, A. (2014). Recurrent models of visual attention. In Advances in Neural Information Processing Systems (pp. 2204-2212).
  96. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., ... & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529-533.
  97. Montero, M.L., Bowers, J.S., Ludwig, C. J., Costa, R. P., Malhotra, G. (2022). Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation. arXiv preprint: http://arxiv.org/abs/2204.02283 · arXiv
  98. Montero, M. L., Ludwig, C. J., Costa, R. P., Malhotra, G., & Bowers, J. (2020, September). The role of disentanglement in generalisation. In International Conference on Learning Representations.
  99. Nguyen, A., Yosinski, J., & Clune, J. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 427-436).
  100. Palmer, S. E. (1999). Color, consciousness, and the isomorphism constraint. Behavioral and Brain Sciences, 22(6), 923-943.
  101. Palmer, S. E. (2003). Visual perception of objects. Handbook of Psychology, 177-211. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  102. Pang, Z., O'May, C. B., Choksi, B., & VanRullen, R. (2021). Predictive coding feedback results in perceived illusory contours in a recurrent neural network. arXiv preprint arXiv:2102.01955. · arXiv
  103. Pater, J. (2019). Generative linguistics and neural networks at 60: Foundation, friction, and fusion. Language, 95(1):e41-e74.
  104. Pessoa, L., Thompson, E., & Noë, A. (1998). Finding out about filling-in: A guide to perceptual completion for visual science and the philosophy of perception. Behavioral and Brain Sciences, 21(6), 723-748
  105. Peterson, J. C., Abbott, J. T., & Griffiths, T. L. (2018). Evaluating (and improving) the correspondence between deep neural networks and human representations. Cognitive Science, 42(8), 2648-2669.
  106. Pinker, S., & Prince, A. (1988). On language and connectionism: Analysis of a parallel distributed processing model of language acquisition. Cognition, 28(1-2), 73-193.
  107. Pomerantz J.R., & Portillo, M.C. (2011). Grouping and Emergent Features in Vision: Toward a Theory of Basic Gestalts. Journal of Experimental Psychology: Human Perception and Performance, 10, 37, 1331- 1349. 10.1037/A0024330 https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press · DOI
  108. Pomerantz, J. R., Sager, L. C., & Stoever, R. J. (1977). Perception of wholes and of their component parts: some configural superiority effects. Journal of Experimental Psychology: Human Perception and Performance, 3, 422-435. https://doi.org/10.1037/0096-1523.3.3.422 · DOI
  109. Popper, K. (2005). The logic of scientific discovery. Routledge.
  110. Puebla, G., & Bowers, J. S. (2022). Can deep convolutional neural networks support relational reasoning in the same-different task?. Journal of Vision, 22(10), 11-11.
  111. Rajalingham, R., Issa, E. B., Bashivan, P., Kar, K., Schmidt, K., & DiCarlo, J. J. (2018). Large-scale, high-resolution comparison of the core visual object recognition behavior of humans, monkeys, and state- of-the-art deep artificial neural networks. Journal of Neuroscience, 38(33), 7255-7269.
  112. Rajalingham, R., Schmidt, K., & DiCarlo, J. J. (2015). Comparison of object recognition behavior in human and monkey. Journal of Neuroscience, 35(35), 12127-12136.
  113. Ramachandran, V. S. (1992). Filling in gaps in perception: Part I. Current Directions in Psychological Science, 1(6), 199-205.
  114. Ramachandran, V. S. (1988). Perception of shape from shading. Nature, 331(6152), 163-166.
  115. Ratan Murty, N. A., Bashivan, P., Abate, A., DiCarlo, J. J., & Kanwisher, N. (2021). Computational models of category-selective brain regions enable high-throughput tests of selectivity. Nature Communications, 12(1), 1-14.
  116. Richards, B. A., Lillicrap, T. P., Beaudoin, P., Bengio, Y., Bogacz, R., Christensen, A., ... & Kording, K. P. (2019). A deep learning framework for neuroscience. Nature Neuroscience, 22(11), 1761-1770.
  117. Ritter, S., Barrett, D. G., Santoro, A., & Botvinick, M. M. (2017, July). Cognitive psychology for deep neural networks: A shape bias case study. In International conference on machine learning (pp. 2940- 2949).
  118. Roberts, S., & Pashler, H. (2000). How persuasive is a good fit? A comment on theory testing. Psychological review, 107(2), 358-367/ doi: 10.1037/0033-295x.107.2.358. · DOI
  119. Rosenfeld A., Zemel R., Tsotsos J.K. (2018). The elephant in the room. arXiv preprint arXiv:1808.03305 · arXiv
  120. Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3), 211-252.
  121. Saarela, T. P., Sayim, B., Westheimer, G., & Herzog, M. H. (2009). Global stimulus configuration modulates crowding. Journal of Vision, 9(2):5, 1-11. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  122. Sabour, S., Frosst, N., & Hinton, G. E. (2017). Dynamic routing between capsules. arXiv preprint arXiv:1710.09829. · arXiv
  123. Santoro, A., Raposo, D., Barrett, D. G., Malinowski, M., Pascanu, R., Battaglia, P., & Lillicrap, T. (2017). A simple neural network module for relational reasoning. Advances in Neural Information Processing Systems, 30, 4967-4976.
  124. Schaeffer, R., Khona, M., & Fiete, I. (2022). No free lunch from deep learning in neuroscience: A case study through models of the entorhinal-hippocampal circuit. bioRxiv.
  125. Schott, L., von Kügelgen, J., Träuble, F., Gehler, P., Russell, C., Bethge, M., ... & Brendel, W. (2021). Visual representation learning does not generalize strongly within the same domain. arXiv preprint arXiv:2107.08221. · arXiv
  126. Schrimpf, M., Blank, I. A., Tuckute, G., Kauf, C., Hosseini, E. A., Kanwisher, N., ... & Fedorenko, E. (2021). The neural architecture of language: Integrative modeling converges on predictive processing. Proceedings of the National Academy of Sciences, 118(45).
  127. Schrimpf, M., Kubilius, J., Hong, H., Majaj, N. J., Rajalingham, R., Issa, E. B., ... & DiCarlo, J. J. (2020a). Brain-score: Which artificial neural network for object recognition is most brain-like? arXiv preprint https://doi.org/10.1101/407007 · DOI
  128. Shah, H., Tamuly, K., Raghunathan, A., Jain, P., & Netrapalli, P. (2020). The pitfalls of simplicity bias in neural networks. arXiv preprint arXiv:2006.07710. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press · arXiv
  129. Simons, D. J., & Levin, D. T. (1997). Change blindness. Trends in Cognitive Sciences, 1(7), 261-267.
  130. Stankiewicz, B. J., & Hummel, J. E. (1996). Categorical relations in shape perception. Spatial Vision, 10(3), 201-236.
  131. Stanley, K. O., Clune, J., Lehman, J., & Miikkulainen, R. (2019). Designing neural networks through neuroevolution. Nature Machine Intelligence, 1(1), 24-35.
  132. Storrs, K. R., Kietzmann, T. C., Walther, A., Mehrer, J., & Kriegeskorte, N. (2021). Diverse deep neural networks all predict human inferior temporal cortex well, after training and fitting. Journal of Cognitive Neuroscience, 33(10), 2044-2064.
  133. Treisman, A. M., & Gelade, G. (1980). A feature-integration theory of attention. Cognitive Psychology, 12(1), 97-136. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  134. Treisman, A., & Schmidt, H. (1982). Illusory conjunctions in the perception of objects. Cognitive Psychology, 14(1), 107-141.
  135. Tsvetkov, C., Malhotra, G., Evans, B., & Bowers, J. (2020). Adding biological constraints to deep neural networks reduces their capacity to learn unstructured data. In Proceedings of the 42nd Annual Conference of the Cognitive Science Society 2020, Toronto, Canada.
  136. Tsvetkov, C., Malhotra, G., Evans, B., & Bowers, J (in press). The Role of Capacity Constraints in Convolutional Neural Networks for Learning Random Versus Natural Data. Neural Networks. https://doi.org/10.1101/2022.03.31.486580 · DOI
  137. Truzzi, A., & Cusack, R. (2020). Convolutional neural networks as a model of visual activity in the brain: Greater contribution of architecture than learned weights. Bridging AI and Cognitive Science. International Conference on Learning Representations.
  138. Tuli, S., Dasgupta, I., Grant, E., & Griffiths, T. L. (2021). Are Convolutional Neural Networks or Transformers more like human vision?. arXiv preprint arXiv:2105.07197. · arXiv
  139. Ullman, S. (1979). The interpretation of structure from motion. Proceedings of the Royal Society of London. Series B. Biological Sciences, 203(1153), 405-426.
  140. Ullman, S., and Basri, R. (1991). Recognition by Linear Combination of Models, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, No. 10, pp. 992-1006.
  141. Vaina, L. M. Makris, N., Kennedy, D., & Cowey, A. (1988). The selective impairment of the perception of first-order motion by unilateral cortical brain damage. Visual Neuroscience, 15, 333-348. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  142. Vankov, I. I., & Bowers, J. S. (2020). Training neural networks to encode symbols enables combinatorial generalization. Philosophical Transactions of the Royal Society B, 375(1791), 20190309.
  143. Wagemans, J., Elder, J. H., Kubovy, M., Palmer, S. E., Peterson, M. A., Singh, M., & von der Heydt, R. (2012). A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure-ground organization. Psychological Bulletin, 138(6), 1172-1217.
  144. Wang, R., Lehman, J., Rawal, A., Zhi, J., Li, Y., Clune, J., & Stanley, K. (2020, November). Enhanced POET: Open-ended reinforcement learning through unbounded invention of learning challenges and their solutions. In International Conference on Machine Learning (pp. 9940-9951).
  145. Wang J, Zhang Z, Xie C, Zhou Y, Premachandran V, Zhu J, Xie L, Yuille A (2018) Visual concepts and compositional voting. Annals of Mathematical Sciences and Applications 2(3):4
  146. Webb, T. W., Sinha, I., & Cohen, J. D. (2021). In International Conference on Learning Representations. https://doi.org/10.48550/arXiv.2012.14601 · DOI
  147. Wolfe, J. M., Cave, K. R., & Franzel, S. L. (1989). Guided search: an alternative to the feature integration model for visual search. Journal of Experimental Psychology: Human Perception and Performance, 15(3), 419-433. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  148. Wolfe, J. M. (1994). Guided search 2.0 a revised model of visual search. Psychonomic Bulletin & Review, 1(2), 202-238.
  149. Wong, Y. K., Twedt, E., Sheinberg, D., & Gauthier, I. (2010). Does Thompson's Thatcher effect reflect a face-specific mechanism? Perception, 39(8), 1125-1141.
  150. Woolley, B. G., & Stanley, K. O. (2011, July). On the deleterious effects of a priori objectives on evolution and representation. In Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation (pp. 957-964).
  151. Xu, Y., & Vaziri-Pashkam, M. (2021). Limits to visual representational correspondence between convolutional neural networks and the human brain. Nature Communications, 12(1), 1-16.
  152. Yamins, D. L., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014). Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proceedings of the National Academy of Sciences, 111(23), 8619-8624.
  153. Young, T., 1802. Bakerian Lecture: On the Theory of Light and Colours. Philosophical Transactions of the Royal Society London, 92:12-48. doi: 10.1098/rstl.1802.0004 · DOI
  154. Zador, A. M. (2019). A critique of pure learning and what artificial neural networks can learn from animal brains. Nature Communications, 10(1), 1-7. https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press
  155. Zhang, R. (2019, May). Making convolutional networks shift-invariant again. In International conference on machine learning (pp. 7324-7334). Proceedings of Machine Learning Research.
  156. Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2017). Understanding deep learning requires rethinking generalization. In 5th International Conference on Learning Representations, Toulon, France, April 24-26.
  157. Zhou, Z., & Firestone, C. (2019). Humans can decipher adversarial images. Nature Communications, 10(1), 1-9.
  158. Zhu, H., Tang, P., Park, J., Park, S., & Yuille, A. (2019). Robustness of object recognition under extreme occlusion in humans and computational models. arXiv preprint arXiv:1905.04598. · arXiv
  159. Zhuang, C., Yan, S., Nayebi, A., Schrimpf, M., Frank, M. C., DiCarlo, J. J., & Yamins, D. L. (2021). Unsupervised neural network models of the ventral visual stream. Proceedings of the National Academy of Sciences, 118(3).
  160. Zou, Z., Shi, Z., Guo, Y., & Ye, J. (2019). Object detection in 20 years: A survey. arXiv preprint arXiv:1905.05055 https://doi.org/10.1017/S0140525X22002813 Published online by Cambridge University Press · arXiv

Cited by

Sorted by citations

Authors
Bowers, J. S., Malhotra, G., Dujmović, M., Llera Montero, M., Tsvetkov, C., Biscione, V., Puebla, G., Adolfi, F., Hummel, J. E., Heaton, R. F., Evans, B. D., Mitchell, J., & Blything, R.
Affiliations
  • University of Bristol (GB)
  • Max Planck Society (DE)
  • University of Illinois Urbana-Champaign (US)
  • University of Sussex (GB)
  • Aston University (GB)
ORCID
Venue
Behavioral and Brain Sciences
Publisher
Cambridge University Press (CUP)
Published
2022-12-01
Volume
46
Pages
e385-e385
ISSN
  • 0140-525X (ISSN-L)
  • 1469-1825
DOI
10.1017/s0140525x22002813
OpenAlex
W4310572212
Cited by
204
References
14
Citations by year
2026: 27 · 2025: 68 · 2024: 43 · 2023: 61 · 2022: 5
FWCI
22.82
Type
journal article
Language
en
Open access
Licence
Locations
  • Behavioral and Brain Sciences (publishedVersion)
  • PubMed (publishedVersion)
  • Aston Publications Explorer (Aston University) (submittedVersion)
  • Figshare (submittedVersion, cc-by)
  • Explore Bristol Research (submittedVersion, cc-by)
  • PsyArXiv (OSF Preprints) (submittedVersion)
  • PsyArXiv (OSF Preprints) (submittedVersion, cc-by)
Funders
European Commission (741134, HORIZON2020)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Visual perception and processing mechanisms
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Face Recognition and Perception
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
deep neural network, object recognition, biological plausibility, human error prediction, fMRI decoding, single-cell responses, explanatory models
MeSH terms
Brain, Humans, Magnetic Resonance Imaging, Vision, Ocular, Visual Perception, Neural Networks, Computer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review