Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Review Article
  • Published:

Capturing the objects of vision with neural networks

Abstract

Human visual perception carves a scene at its physical joints, decomposing the world into objects, which are selectively attended, tracked and predicted as we engage our surroundings. Object representations emancipate perception from the sensory input, enabling us to keep in mind that which is out of sight and to use perceptual content as a basis for action and symbolic cognition. Human behavioural studies have documented how object representations emerge through grouping, amodal completion, proto-objects and object files. By contrast, deep neural network models of visual object recognition remain largely tethered to sensory input, despite achieving human-level performance at labelling objects. Here, we review related work in both fields and examine how these fields can help each other. The cognitive literature provides a starting point for the development of new experimental tasks that reveal mechanisms of human object perception and serve as benchmarks driving the development of deep neural network models that will put the object into object recognition.

This is a preview of subscription content, access via your institution

Access options

Buy this article

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Stages of untethering human visual object perception from the sensorium.
Fig. 2: Completion phenomena.
Fig. 3: Neural network mechanisms for untethering.
Fig. 4: Space of tasks for untethered object perception.

Similar content being viewed by others

References

  1. Von Helmholtz, H. Handbuch der Physiologischen Optik (Voss, 1867).

  2. Yuille, A. & Kersten, D. Vision as Bayesian inference: analysis by synthesis? Trends Cogn. Sci. 10, 301–308 (2006).

    Article  PubMed  Google Scholar 

  3. Pearl, J. Causality (Cambridge Univ. Press, 2009).

  4. Piaget, J. The Construction of Reality in the Child (Basic Books, 1954).

  5. Adelson, E. H. On seeing stuff: the perception of materials by humans and machines. In Human Vision and Electronic Imaging VI (eds. Rogowitz, B. E. & Pappas, T. N.) vol. 4299 1–12 (SPIE, 2001).

  6. Clowes, M. B. On seeing things. Artif. Int. 2, 79–116 (1971).

    Article  Google Scholar 

  7. Julesz, B. Experiments in the visual perception of texture. Sci. Am. 232, 34–43 (1975).

    Article  CAS  PubMed  Google Scholar 

  8. Simoncelli, E. P. & Olshausen, B. A. Natural image statistics and neural representation. Ann. Rev. Neurosci. 24, 1193–1216 (2001).

    Article  CAS  PubMed  Google Scholar 

  9. Rosenholtz, R., Li, Y. & Nakano, L. Measuring visual clutter. J. Vis. 7, 17–17 (2007).

    Article  PubMed  Google Scholar 

  10. Hoffman, D. D. & Richards, W. A. Parts of recognition. Cognition 18, 65–96 (1984).

    Article  CAS  PubMed  Google Scholar 

  11. Michotte, A. et al. Les Complements Amodaux des Structures Perceptives (Institut de psychologie de l’Université de Louvain, 1964).

  12. Rensink, R. A. The dynamic representation of scenes. Visual Cogn. 7, 17–42 (2000).

    Article  Google Scholar 

  13. Gregory, R. L. Perceptions as hypotheses. Phil. Trans. R. Soc. Lond. B Biol. Sci. 290, 181–197 (1980).

    Article  CAS  Google Scholar 

  14. Rock, I. Indirect Perception (The MIT Press, 1997).

  15. Clark, A. Whatever next? Predictive brains, situated agents, and the future of cognitive science. Behav. Brain Sci. 36, 181–204 (2013).

    Article  PubMed  Google Scholar 

  16. Friston, K. J. A theory of cortical responses. Phil. Trans. R. Soc. B Biol. Sci. 360, 815–836 (2005).

    Article  Google Scholar 

  17. van Steenkiste, S., Greff, K. & Schmidhuber, J. A perspective on objects and systematic generalization in model-based RL. Preprint at http://arxiv.org/abs/1906.01035 (2019).

  18. Greff, K., van Steenkiste, S. & Schmidhuber, J. On the binding problem in artificial neural networks. Preprint at http://arxiv.org/abs/2012.05208 (2020).

  19. Spelke, E. S. Principles of object perception. Cogn. Sci. 14, 29–56 (1990).

    Article  Google Scholar 

  20. Scholl, B. J. Object persistence in philosophy and psychology. Mind Lang. 22, 563–591 (2007).

    Article  Google Scholar 

  21. Sarkka, S. Bayesian Filtering and Smoothing (Cambridge Univ. Press, 2013).

  22. Deneve, S., Duhamel, J.-R. & Pouget, A. Optimal sensorimotor integration in recurrent cortical networks: a neural implementation of Kalman filters. J. Neurosci. 27, 5744–5756 (2007).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. LeCun, Y. et al. Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 541–551 (1989).

    Article  Google Scholar 

  24. Fukushima, K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193–202 (1980).

    Article  CAS  PubMed  Google Scholar 

  25. Geirhos, R. et al. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In Proc. 7th International Conference on Learning Representations (OpenReview.net, 2019).

  26. Kansky, K. et al. Schema networks: zero-shot transfer with a generative causal model of intuitive physics. In Proc. 34th International Conference on Machine Learning (eds. Precup, D. & Teh, Y. W.) vol. 70 1809–1818 (PMLR, 2017).

  27. Lake, B. M., Ullman, T. D., Tenenbaum, J. B. & Gershman, S. J. Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017).

    Article  PubMed  Google Scholar 

  28. Yildirim, I., Wu, J., Kanwisher, N. & Tenenbaum, J. An integrative computational architecture for object-driven cortex. Curr. Opin. Neurobiol. 55, 73–81 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. Golan, T., Raju, P. C. & Kriegeskorte, N. Controversial stimuli: pitting neural networks against each other as models of human cognition. Proc. Natl Acad. Sci. 117, 29330–29337 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Gibson, J. J. The Ecological Approach to Visual Perception: Classic Edition (Houghton Mifflin, 1979).

  31. Knill, D. C. & Pouget, A. The Bayesian brain: the role of uncertainty in neural coding and computation. Trends Neurosci. 27, 712–719 (2004).

    Article  CAS  PubMed  Google Scholar 

  32. Treisman, A. The binding problem. Curr. Opin. Neurobiol. 6, 171–178 (1996).

    Article  CAS  PubMed  Google Scholar 

  33. von der Malsburg, C. The Correlation Theory of Brain Function. in Models of Neural Networks: Temporal Aspects of Coding and Information Processing in Biological Systems (eds. Domany, E., van Hemmen, J. L. & Schulten, K.) 95–119 (Springer, 1981).

  34. Duncan, J. Selective attention and the organization of visual information. J. Exp. Psychol. Gen. 113, 501–517 (1984).

    Article  CAS  PubMed  Google Scholar 

  35. Neisser, U. Cognitive Psychology (Appleton-Century-Crofts, 1967).

  36. Treisman, A. Features and objects in visual processing. Sci. Am. 255, 114–125 (1986).

    Article  Google Scholar 

  37. Baars, B. J. A Cognitive Theory of Consciousness (Cambridge Univ. Press, 1993).

  38. Dehaene, S. & Naccache, L. Towards a cognitive neuroscience of consciousness: basic evidence and a workspace framework. Cognition 79, 1–37 (2001).

    Article  CAS  PubMed  Google Scholar 

  39. Hubel, D. H. & Wiesel, T. N. Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J. Neurophysiol. 28, 229–289 (1965).

    Article  CAS  PubMed  Google Scholar 

  40. Riesenhuber, M. & Poggio, T. Hierarchical models of object recognition in cortex. Nat. Neurosci. 2, 1019–1025 (1999).

    Article  CAS  PubMed  Google Scholar 

  41. Roelfsema, P. R. Cortical algorithms for perceptual grouping. Ann. Rev. Neurosci. 29, 203–227 (2006).

    Article  CAS  PubMed  Google Scholar 

  42. Field, D. J., Hayes, A. & Hess, R. F. Contour integration by the human visual system: evidence for a local ‘association field’. Vis. Res. 33, 173–193 (1993).

    Article  CAS  PubMed  Google Scholar 

  43. Geisler, W. S. Visual perception and the statistical properties of natural scenes. Ann. Rev. Psychol. 59, 167–192 (2008).

    Article  Google Scholar 

  44. Bosking, W. H., Zhang, Y., Schofield, B. & Fitzpatrick, D. Orientation selectivity and the arrangement of horizontal connections in tree shrew striate cortex. J. Neurosci. 17, 2112–2127 (1997).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  45. Koffka, K. Principles of Gestalt Psychology (Harcourt, Brace, 1935).

  46. Rock, I. & Palmer, S. The legacy of gestalt psychology. Sci. Am. 263, 84–91 (1990).

    Article  CAS  PubMed  Google Scholar 

  47. Wertheimer, M. Untersuchungen zur lehre von der gestalt. Psychol. Forsch. 4, 301–350 (1923).

    Article  Google Scholar 

  48. Nakayama, K. & Shimojo, S. Experiencing and perceiving visual surfaces. Science 257, 1357–1363 (1992).

    Article  CAS  PubMed  Google Scholar 

  49. Rosenholtz, R., Twarog, N. R., Schinkel-Bielefeld, N. & Wattenberg, M. An intuitive model of perceptual grouping for HCI design. In Proc. SIGCHI Conference on Human Factors in Computing Systems 1331–1340 (ACM, 2009).

  50. Li, Z. A neural model of contour integration in the primary visual cortex. Neural Comput. 10, 903–940 (1998).

    Article  CAS  PubMed  Google Scholar 

  51. Yen, S.-C. & Finkel, L. H. Extraction of perceptually salient contours by striate cortical networks. Vis. Res. 38, 719–741 (1998).

    Article  CAS  PubMed  Google Scholar 

  52. Roelfsema, P. R., Lamme, V. A. & Spekreijse, H. Object-based attention in the primary visual cortex of the macaque monkey. Nature 395, 376–381 (1998).

    Article  CAS  PubMed  Google Scholar 

  53. Nakayama, K. & Silverman, G. H. Serial and parallel processing of visual feature conjunctions. Nature 320, 264–265 (1986).

    Article  CAS  PubMed  Google Scholar 

  54. Alais, D., Blake, R. & Lee, S.-H. Visual features that vary together over time group together over space. Nat. Neurosci. 1, 160–164 (1998).

    Article  CAS  PubMed  Google Scholar 

  55. Vecera, S. P. & Farah, M. J. Is visual image segmentation a bottom-up or an interactive process? Percept. Psychophys. 59, 1280–1296 (1997).

    Article  CAS  PubMed  Google Scholar 

  56. Sekuler, A. & Palmer, S. Perception of partly occluded objects: a microgenetic analysis. J. Exp. Psychol. Gen. 121, 95–111 (1992).

    Article  Google Scholar 

  57. Marr, D., Ullman, S. & Poggio, T. Vision: A Computational Investigation Into the Human Representation and Processing of Visual Information (W. H. Freeman, 1982) .

  58. Michotte, A. & Burke, L. Une nouvelle enigme dans la psychologie de la perception: le’donne amodal’dans l’experience sensorielle. In Proc. XIII Congrés Internationale de Psychologie 179–180 (1951).

  59. Komatsu, H. The neural mechanisms of perceptual filling-in. Nat. Rev. Neurosci. 7, 220–231 (2006).

    Article  CAS  PubMed  Google Scholar 

  60. Shore, D. I. & Enns, J. T. Shape completion time depends on the size of the occluded region. J. Exp. Psychol. Hum. Percept. Perform. 23, 980–998 (1997).

    Article  CAS  PubMed  Google Scholar 

  61. He, Z. J. & Nakayama, K. Surfaces versus features in visual search. Nature 359, 231–233 (1992).

    Article  CAS  PubMed  Google Scholar 

  62. Rensink, R. A. & Enns, J. T. Early completion of occluded objects. Vis. Res. 38, 2489–2505 (1998).

    Article  CAS  PubMed  Google Scholar 

  63. Kellman, P. J. & Shipley, T. F. A theory of visual interpolation in object perception. Cogn. Psychol. 23, 141–221 (1991).

    Article  CAS  PubMed  Google Scholar 

  64. Tse, P. U. Volume completion. Cogn. Psychol. 39, 37–68 (1999).

    Article  CAS  PubMed  Google Scholar 

  65. Buffart, H., Leeuwenberg, E. & Restle, F. Coding theory of visual pattern completion. J. Exp. Psychol. Hum. Percept. Perform. 7, 241–274 (1981).

    Article  CAS  PubMed  Google Scholar 

  66. Weigelt, S., Singer, W. & Muckli, L. Separate cortical stages in amodal completion revealed by functional magnetic resonance adaptation. BMC Neurosci. 8, 70 (2007).

    Article  PubMed  PubMed Central  Google Scholar 

  67. Thielen, J., Bosch, S. E., van Leeuwen, T. M., van Gerven, M. A. J. & van Lier, R. Neuroimaging findings on amodal completion: a review. i-Perception 10, 2041669519840047 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  68. Mooney, C. M. Age in the development of closure ability in children. Can. J. Psychol. 11, 219–226 (1957).

    Article  CAS  PubMed  Google Scholar 

  69. Snodgrass, J. G. & Feenan, K. Priming effects in picture fragment completion: support for the perceptual closure hypothesis. J. Exp. Psychol. Gen. 119, 276–296 (1990).

    Article  CAS  PubMed  Google Scholar 

  70. Treisman, A. & Gelade, G. A feature-integration theory of attention. Cogn. Psychol. 12, 97–136 (1980).

    Article  CAS  PubMed  Google Scholar 

  71. Pylyshyn, Z. W. Is vision continuous with cognition? The case for cognitive impenetrability of visual perception. Behav. Brain Sci. 22, 341–365 (1999).

    Article  CAS  PubMed  Google Scholar 

  72. Wolfe, J. M. & Cave, K. R. The psychophysical evidence for a binding problem in human vision. Neuron 24, 11–17 (1999).

    Article  CAS  PubMed  Google Scholar 

  73. Ullman, S. The interpretation of structure from motion. Proc. R. Soc. Lon. B Biol. Sci. 203, 405–426 (1979).

    Article  CAS  Google Scholar 

  74. Flombaum, J. I., Scholl, B. J. & Santos, L. R. Spatiotemporal priority as a fundamental principle of object persistence. In The Origins of Object Knowledge (eds. Hood, B. M. & Santos, L. R.) 135–164 (Oxford University Press, 2009).

  75. Mitroff, S. R. & Alvarez, G. A. Space and time, not surface features, guide object persistence. Psychon. Bull. Rev. 14, 1199–1204 (2007).

    Article  PubMed  Google Scholar 

  76. Burke, L. On the tunnel effect. Quart. J. Exp. Psychol. 4, 121–138 (1952).

    Article  Google Scholar 

  77. Flombaum, J. I. & Scholl, B. J. A temporal same-object advantage in the tunnel effect: facilitated change detection for persisting objects. J. Exp. Psychol. Hum. Percept. Perform. 32, 840–853 (2006).

    Article  PubMed  Google Scholar 

  78. Hollingworth, A. & Franconeri, S. L. Object correspondence across brief occlusion is established on the basis of both spatiotemporal and surface feature cues. Cognition 113, 150–166 (2009).

    Article  PubMed  PubMed Central  Google Scholar 

  79. Moore, C. M., Stephens, T. & Hein, E. Features, as well as space and time, guide object persistence. Psychon. Bull. Rev. 17, 731–736 (2010).

    Article  PubMed  PubMed Central  Google Scholar 

  80. Papenmeier, F., Meyerhoff, H. S., Jahn, G. & Huff, M. Tracking by location and features: object correspondence across spatiotemporal discontinuities during multiple object tracking. J. Exp. Psychol. Hum. Percept. Perform. 40, 159–171 (2014).

    Article  PubMed  Google Scholar 

  81. Liberman, A., Zhang, K. & Whitney, D. Serial dependence promotes object stability during occlusion. J. Vis. 16, 16 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  82. Fischer, C. et al. Context information supports serial dependence of multiple visual objects across memory episodes. Nat. Commun. 11, 1932 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  83. Irwin, D. E. Memory for position and identity across eye movements. J. Exp. Psychol. Learn. Mem. Cogn. 18, 307–317 (1992).

    Article  Google Scholar 

  84. Richard, A. M., Luck, S. J. & Hollingworth, A. Establishing object correspondence across eye movements: flexible use of spatiotemporal and surface feature information. Cognition 109, 66–88 (2008).

    Article  PubMed  PubMed Central  Google Scholar 

  85. Kahneman, D., Treisman, A. & Gibbs, B. J. The reviewing of object-files: object specific integration of information. Cogn. Psychol. 24, 174–219 (1992).

    Article  Google Scholar 

  86. Pylyshyn, Z. W. The role of location indexes in spatial perception: a sketch of the FINST spatial-index model. Cognition 32, 65–97 (1989).

    Article  CAS  PubMed  Google Scholar 

  87. Itti, L. & Koch, C. Computational modelling of visual attention. Nat. Rev. Neurosci. 2, 194–203 (2001).

    Article  CAS  PubMed  Google Scholar 

  88. Cavanagh, P. & Alvarez, G. A. Tracking multiple targets with multifocal attention. Trends Cogn. Sci. 9, 349–354 (2005).

    Article  PubMed  Google Scholar 

  89. Bahcall, D. O. & Kowler, E. Attentional interference at small spatial separations. Vis. Res. 39, 71–86 (1999).

    Article  CAS  PubMed  Google Scholar 

  90. Franconeri, S. L., Alvarez, G. A. & Cavanagh, P. Flexible cognitive resources: competitive content maps for attention and memory. Trends Cogn. Sci. 17, 134–141 (2013).

    Article  PubMed  PubMed Central  Google Scholar 

  91. Pylyshyn, Z. W. & Storm, R. W. Tracking multiple independent targets: evidence for a parallel tracking mechanism. Spatial Vis. 3, 179–197 (1988).

    Article  CAS  Google Scholar 

  92. Intriligator, J. & Cavanagh, P. The spatial resolution of visual attention. Cognit. Psychol. 43, 171–216 (2001).

    Article  CAS  PubMed  Google Scholar 

  93. Scholl, B. J. & Pylyshyn, Z. W. Tracking multiple items through occlusion: clues to visual objecthood. Cognit. Psychol. 38, 259–290 (1999).

    Article  CAS  PubMed  Google Scholar 

  94. Yantis, S. Multielement visual tracking: attention and perceptual organization. Cognit. Psychol. 24, 295–340 (1992).

    Article  CAS  PubMed  Google Scholar 

  95. Vul, E., Alvarez, G., Tenenbaum, J. B. & Black, M. J. Explaining human multiple object tracking as resource-constrained approximate inference in a dynamic probabilistic model. In Proc. Advances in Neural Information Processing Systems 22 (eds Bengio, Y. et al.) 1955–1963 (Curran Associates, 2009).

  96. Alvarez, G. A. & Franconeri, S. L. How many objects can you track? Evidence for a resource-limited attentive tracking mechanism. J. Vis. 7, 14 (2007).

    Article  PubMed  Google Scholar 

  97. Flombaum, J. I., Scholl, B. J. & Pylyshyn, Z. W. Attentional resources in visual tracking through occlusion: the high-beams effect. Cognition 107, 904–931 (2008).

    Article  PubMed  Google Scholar 

  98. Vecera, S. P. & Farah, M. J. Does visual attention select objects or locations? J. Exp. Psychol. Gen. 123, 146–160 (1994).

    Article  CAS  PubMed  Google Scholar 

  99. Chen, Z. Object-based attention: a tutorial review. Atten. Percept. Psychophys. 74, 784–802 (2012).

    Article  PubMed  Google Scholar 

  100. Egly, R., Driver, J. & Rafal, R. D. Shifting visual attention between objects and locations: evidence from normal and parietal lesion subjects. J. Exp. Psychol. Gen. 123, 161–177 (1994).

    Article  CAS  PubMed  Google Scholar 

  101. Houtkamp, R., Spekreijse, H. & Roelfsema, P. R. A gradual spread of attention. Percept. Psychophys. 65, 1136–1144 (2003).

    Article  CAS  PubMed  Google Scholar 

  102. Jeurissen, D., Self, M. W. & Roelfsema, P. R. Serial grouping of 2D-image regions with object-based attention in humans. eLife 5, e14320 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  103. Moore, C. M., Yantis, S. & Vaughan, B. Object-based visual selection: evidence from perceptual completion. Psychol. Sci. 9, 104–110 (1998).

    Article  Google Scholar 

  104. Peters, B., Kaiser, J., Rahm, B. & Bledowski, C. Activity in human visual and parietal cortex reveals object-based attention in working memory. J. Neurosci. 35, 3360–3369 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  105. Peters, B., Kaiser, J., Rahm, B. & Bledowski, C. Object-based attention prioritizes working memory contents at a theta rhythm. J. Exp. Psychol. Gen. (2020).

  106. Baillargeon, R. Object permanence in 3 1/2- and 4 1/2-month-old infants. Dev. Psychol. 23, 655–664 (1987).

    Article  Google Scholar 

  107. Baillargeon, R., Spelke, E. S. & Wasserman, S. Object permanence in five-month-old infants. Cognition 20, 191–208 (1985).

    Article  CAS  PubMed  Google Scholar 

  108. Spelke, E. S., Breinlinger, K., Macomber, J. & Jacobson, K. Origins of knowledge. Psychol. Rev. 99, 605–632 (1992).

    Article  CAS  PubMed  Google Scholar 

  109. Wilcox, T. Object individuation: infants’ use of shape, size, pattern, and color. Cognition 72, 125–166 (1999).

    Article  CAS  PubMed  Google Scholar 

  110. Rosander, K. & von Hofsten, C. Infants’ emerging ability to represent occluded object motion. Cognition 91, 1–22 (2004).

    Article  PubMed  Google Scholar 

  111. Moore, M. K., Borton, R. & Darby, B. L. Visual tracking in young infants: evidence for object identity or object permanence? J. Exp. Child Psychol. 25, 183–198 (1978).

    Article  CAS  PubMed  Google Scholar 

  112. Freyd, J. J. & Finke, R. A. Representational momentum. J. Exp. Psychol. Learn. Mem. Cognit. 10, 126–132 (1984).

    Article  Google Scholar 

  113. Benguigui, N., Ripoll, H. & Broderick, M. P. Time-to-contact estimation of accelerated stimuli is based on first-order information. J. Exp. Psychol. Hum. Percept. Perform. 29, 1083–1101 (2003).

    Article  PubMed  Google Scholar 

  114. Rosenbaum, D. A. Perception and extrapolation of velocity and acceleration. J. Exp. Psychol. Hum. Percept. Perform. 1, 395–403 (1975).

    Article  CAS  PubMed  Google Scholar 

  115. Franconeri, S. L., Pylyshyn, Z. W. & Scholl, B. J. A simple proximity heuristic allows tracking of multiple objects through occlusion. Atten. Percept. Psychophys. 74, 691–702 (2012).

    Article  PubMed  Google Scholar 

  116. Matin, E. Saccadic suppression: a review and an analysis. Psychol. Bull. 81, 899–917 (1974).

    Article  CAS  PubMed  Google Scholar 

  117. Henderson, J. M. Two representational systems in dynamic visual identification. J. Exp. Psychol. Gen. 123, 410–426 (1994).

    Article  CAS  PubMed  Google Scholar 

  118. Bahrami, B. Object property encoding and change blindness in multiple object tracking. Visual Cogn. 10, 949–963 (2003).

    Article  Google Scholar 

  119. Pylyshyn, Z. Some puzzling findings in multiple object tracking: I. Tracking without keeping track of object identities. Visual Cogn. 11, 801–822 (2004).

    Article  Google Scholar 

  120. Horowitz, T. S. et al. Tracking unique objects. Percept. Psychophys. 69, 172–184 (2007).

    Article  PubMed  Google Scholar 

  121. Fougnie, D. & Marois, R. Distinct capacity limits for attention and working memory: evidence from attentive tracking and visual working memory paradigms. Psychol. Sci. 17, 526–534 (2006).

    Article  PubMed  Google Scholar 

  122. Hollingworth, A. & Rasmussen, I. P. Binding objects to locations: the relationship between object files and visual working memory. J. Exp. Psychol. Hum. Percept. Perform. 36, 543–564 (2010).

    Article  PubMed  PubMed Central  Google Scholar 

  123. Awh, E., Barton, B. & Vogel, E. K. Visual working memory represents a fixed number of items regardless of complexity. Psychol. Sci. 18, 622–628 (2007).

    Article  PubMed  Google Scholar 

  124. Cowan, N. The magical number 4 in short-term memory: a reconsideration of mental storage capacity. Behav. Brain Sci. 24, 87–114 (2001).

    Article  CAS  PubMed  Google Scholar 

  125. Luck, S. J. & Vogel, E. K. The capacity of visual working memory for features and conjunctions. Nature 390, 279–284 (1997).

    Article  CAS  PubMed  Google Scholar 

  126. Miller, G. A. The magical number seven. Psychol. Rev. 63, 81–97 (1956).

    Article  CAS  PubMed  Google Scholar 

  127. Bays, P. M., Wu, E. Y. & Husain, M. Storage and binding of object features in visual working memory. Neuropsychologia 49, 1622–1631 (2011).

    Article  PubMed  Google Scholar 

  128. Fougnie, D. & Alvarez, G. A. Object features fail independently in visual working memory: evidence for a probabilistic feature-store model. J. Vis. 11, 3 (2011).

    Article  PubMed  Google Scholar 

  129. Brady, T. F., Konkle, T. & Alvarez, G. A. A review of visual memory capacity: beyond individual items and toward structured representations. J. Vis. 11, 4 (2011).

    Article  PubMed  Google Scholar 

  130. Alvarez, G. A. & Cavanagh, P. The capacity of visual short-term memory is set both by visual information load and by number of objects. Psychol. Sci. 15, 106–111 (2004).

    Article  CAS  PubMed  Google Scholar 

  131. Bays, P. M. & Husain, M. Dynamic shifts of limited working memory resources in human vision. Science 321, 851–854 (2008).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  132. Wilken, P. & Ma, W. J. A detection theory account of change detection. J. Vis. 4, 1120–1135 (2004).

    Article  PubMed  Google Scholar 

  133. Oberauer, K. & Lin, H.-Y. An interference model of visual working memory. Psychol. Rev. 124, 21–59 (2017).

    Article  PubMed  Google Scholar 

  134. Bouchacourt, F. & Buschman, T. J. A flexible model of working memory. Neuron 103, 147–160 (2019).

    Article  CAS  Google Scholar 

  135. Baddeley, A. D. & Hitch, G. Working Memory. In Psychology of Learning and Motivation (ed. Bower, G. H.) vol. 8 47–89 (Academic, 1974).

  136. Cowan, N. Evolving conceptions of memory storage, selective attention, and their mutual constraints within the human information-processing system. Psychol. Bull. 104, 163–191 (1988).

    Article  CAS  PubMed  Google Scholar 

  137. Miyake, A. & Shah, P. Models of Working Memory: Mechanisms of Active Maintenance and Executive Control (Cambridge Univ. Press, 1999).

  138. McCulloch, W. S. & Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biol. 5, 115–133 (1943).

    Google Scholar 

  139. O’Reilly, R. C. & Munakata, Y. Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain (MIT Press, 2000).

  140. Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Proc. Advances in Neural Information Processing Systems 25 (eds. Pereira, F. et al.) (Curran Associates, 2012).

  141. Rosenblatt, F. Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms Technical Report (Cornell Aeronautical Lab, 1961).

  142. Rumelhart, D. E., Hinton, G. E. & Williams, R. J. Learning representations by back-propagating errors. Nature 323, 533–536 (1986).

    Article  Google Scholar 

  143. Ivakhnenko, A. G. Polynomial theory of complex systems. In Proc. IEEE transactions on Systems, Man, and Cybernetics 364–378 (IEEE, 1971).

  144. Hebb, D. O. The Organization of Behavior: A Neuropsychological Theory (J. Wiley, Chapman & Hall, 1949).

  145. Hopfield, J. J. Neural networks and physical systems with emergent collective computational abilities. Proc. Natl Acad. Sci. USA 79, 2554–2558 (1982).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  146. Zemel, R. S. & Mozer, M. C. Localist attractor networks. Neural Comput. 13, 1045–1064 (2001).

    Article  CAS  PubMed  Google Scholar 

  147. Schmidhuber, J. Learning to control fast-weight memories: an alternative to dynamic recurrent networks. Neural Comput. 4, 131–139 (1992).

    Article  Google Scholar 

  148. Olshausen, B. A., Anderson, C. H. & Essen, D. V. A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. J. Neurosci. 13, 4700–4719 (1993).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  149. Anderson, C. H. & Van Essen, D. C. Shifter circuits: a computational strategy for dynamic aspects of visual processing. Proc. Natl Acad. Sci. USA 84, 6297–6301 (1987).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  150. Burak, Y., Rokni, U., Meister, M. & Sompolinsky, H. Bayesian model of dynamic image stabilization in the visual system. Proc. Natl Acad. Sci. USA 107, 19525–19530 (2010).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  151. Salinas, E. & Thier, P. Gain modulation: a major computational principle of the central nervous system. Neuron 27, 15–21 (2000).

    Article  CAS  PubMed  Google Scholar 

  152. Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput 9, 1735–1780 (1997).

    Article  CAS  PubMed  Google Scholar 

  153. Reichert, D. P. & Serre, T. Neuronal synchrony in complex-valued deep networks. In Proc. 2nd International Conference on Learning Representations (2014).

  154. Gray, C. M. & Singer, W. Stimulus-specific neuronal oscillations in orientation columns of cat visual cortex. Proc. Natl Acad. Sci. USA 86, 1698–1702 (1989).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  155. Hummel, J. E. & Biederman, I. Dynamic binding in a neural network for shape recognition. Psychol. Rev. 99, 480–517 (1992).

    Article  CAS  PubMed  Google Scholar 

  156. Fries, P. Rhythms for cognition: communication through coherence. Neuron 88, 220–235 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  157. Rao, R. P. N. & Ballard, D. H. Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nat. Neurosci. 2, 79–87 (1999).

    Article  CAS  PubMed  Google Scholar 

  158. Higgins, I. et al. Towards a definition of disentangled representations. Preprint at http://arxiv.org/abs/1812.02230 (2018).

  159. Feldman, J. What is a visual object? Trends Cogn. Sci. 7, 252–256 (2003).

    Article  PubMed  Google Scholar 

  160. Pouget, A., Beck, J. M., Ma, W. J. & Latham, P. E. Probabilistic brains: knowns and unknowns. Nat. Neurosci. 16, 1170–1178 (2013).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  161. Lee, T. S. & Mumford, D. Hierarchical Bayesian inference in the visual cortex. JOSA A 20, 1434–1448 (2003).

    Article  PubMed  Google Scholar 

  162. Dayan, P., Hinton, G. E., Neal, R. M. & Zemel, R. S. The Helmholtz machine. Neural Comput. 7, 889–904 (1995).

    Article  CAS  PubMed  Google Scholar 

  163. Stuhlmüller, A., Taylor, J. & Goodman, N. Learning stochastic inverses. In Proc. Advances in Neural Information Processing Systems 26 (eds Burges, C. J. et al.) 3048–3056 (Curran Associates, 2013).

  164. Bergen, R. S. van. & Kriegeskorte, N. Going in circles is the way forward: the role of recurrence in visual inference. Curr. Opinion Neurobiol. 65, 176–193 (2020).

    Article  CAS  Google Scholar 

  165. von der Heydt, R., Friedman, H. S. & Zhou, H. Searching for the neural mechanisms of color filling-in. In Filling-in: From perceptual completion to cortical reorganization (eds. Pessoa, L. & De Weerd, P.) 106–127 (Oxford Univ. Press, 2003).

  166. Kogo, N. & Wagemans, J. The ‘side’ matters: how configurality is reflected in completion. Cogn. Neurosci. 4, 31–45 (2013).

    Article  PubMed  Google Scholar 

  167. Craft, E., Schütze, H., Niebur, E. & von der Heydt, R. A neural model of figure-ground organization. J. Neurophysiol. 97, 4310–4326 (2007).

    Article  PubMed  Google Scholar 

  168. Grossberg, S. & Mingolla, E. Neural dynamics of form perception: boundary completion, illusory figures, and neon color spreading. Psychol. Rev. 92, 173–211 (1985).

    Article  CAS  PubMed  Google Scholar 

  169. Mingolla, E., Ross, W. & Grossberg, S. A neural network for enhancing boundaries and surfaces in synthetic aperture radar images. Neural Netw. 12, 499–511 (1999).

    Article  PubMed  Google Scholar 

  170. Zhaoping, L. Border ownership from intracortical interactions in visual area V2. Neuron 47, 143–153 (2005).

    Article  PubMed  CAS  Google Scholar 

  171. Fukushima, K. Neural network model for completing occluded contours. Neural Netw. 23, 528–540 (2010).

    Article  PubMed  Google Scholar 

  172. Tu, Z. & Zhu, S.-C. Image segmentation by data-driven Markov chain Monte Carlo. IEEE Trans. Pattern Anal. 24, 657–673 (2002).

    Article  Google Scholar 

  173. Fukushima, K. Restoring partly occluded patterns: a neural network model. Neural Netw. 18, 33–43 (2005).

    Article  PubMed  Google Scholar 

  174. Lücke, J., Turner, R., Sahani, M. & Henniges, M. Occlusive components analysis. In Proc. Advances in Neural Information Processing Systems 22 (eds Bengio, Y. et al.) 1069–1077 (Curran Associates, 2009).

  175. Johnson, J. S. & Olshausen, B. A. The recognition of partially visible natural objects in the presence and absence of their occluders. Vis. Res. 45, 3262–3276 (2005).

    Article  PubMed  Google Scholar 

  176. Koch, C. & Ullman, S. Shifts in Selective Visual Attention: Towards the Underlying Neural Circuitry. In Matters of Intelligence: Conceptual Structures in Cognitive Neuroscience (ed. Vaina, L. M.) 115–141 (Springer, 1987).

  177. Tsotsos, J. K. et al. Modeling visual-attention via selective tuning. Artif. Int. 78, 507–545 (1995).

    Article  Google Scholar 

  178. Walther, D. & Koch, C. Modeling attention to salient proto-objects. Neural Netw. 19, 1395–1407 (2006).

    Article  PubMed  Google Scholar 

  179. Kazanovich, Y. & Borisyuk, R. An oscillatory neural model of multiple object tracking. Neural Comput. 18, 1413–1440 (2006).

    Article  PubMed  Google Scholar 

  180. Libby, A. & Buschman, T. J. Rotational dynamics reduce interference between sensory and memory representations. Nat. Neurosci. https://doi.org/10.1038/s41593-021-00821-9 (2021).

  181. Barak, O. & Tsodyks, M. Working models of working memory. Curr. Opin. Neurobiol. 25, 20–24 (2014).

    Article  CAS  PubMed  Google Scholar 

  182. Durstewitz, D., Seamans, J. K. & Sejnowski, T. J. Neurocomputational models of working memory. Nat. Neurosci. 3, 1184–1191 (2000).

    Article  CAS  PubMed  Google Scholar 

  183. Compte, A. Synaptic mechanisms and network dynamics underlying spatial working memory in a cortical network model. Cerebral Cortex 10, 910–923 (2000).

    Article  CAS  PubMed  Google Scholar 

  184. Wang, X.-J. Synaptic reverberations underlying mnemonic persistent activity. Trends Neurosci. 24, 455–463 (2001).

    Article  CAS  PubMed  Google Scholar 

  185. Wimmer, K., Nykamp, D. Q., Constantinidis, C. & Compte, A. Bump attractor dynamics in prefrontal cortex explains behavioral precision in spatial working memory. Nature Neurosci. 17, 431–439 (2014).

    Article  CAS  PubMed  Google Scholar 

  186. Zenke, F., Agnes, E. J. & Gerstner, W. Diverse synaptic plasticity mechanisms orchestrated to form and retrieve memories in spiking neural networks. Nat. Commun. 6, 6922 (2015).

    Article  CAS  PubMed  Google Scholar 

  187. Mareschal, D., Plunkett, K. & Harris, P. A computational and neuropsychological account of object-oriented behaviours in infancy. Developmental Science 2, 306–317 (1999).

    Article  Google Scholar 

  188. Munakata, Y., Mcclelland, J. L., Johnson, M. H. & Siegler, R. S. Rethinking infant knowledge: toward an adaptive process account of successes and failures in object permanence tasks. Psychol. Rev. 104, 686–713 (1997).

    Article  CAS  PubMed  Google Scholar 

  189. Mi, Y., Katkov, M. & Tsodyks, M. Synaptic correlates of working memory capacity. Neuron 93, 323–330 (2017).

    Article  CAS  PubMed  Google Scholar 

  190. Mongillo, G., Barak, O. & Tsodyks, M. Synaptic theory of working memory. Science 319, 1543–1546 (2008).

    Article  CAS  PubMed  Google Scholar 

  191. Masse, N. Y., Yang, G. R., Song, H. F., Wang, X.-J. & Freedman, D. J. Circuit mechanisms for the maintenance and manipulation of information in working memory. Nat. Neurosci. 22, 1159–1167 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  192. Chatham, C. H. & Badre, D. Multiple gates on working memory. Curr. Opin. Behav. Sci. 1, 23–31 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  193. Frank, M. J., Loughry, B. & O’Reilly, R. C. Interactions between frontal cortex and basal ganglia in working memory: a computational model. Cognitive 1, 137–160 (2001).

    CAS  Google Scholar 

  194. Gruber, A. J., Dayan, P., Gutkin, B. S. & Solla, S. A. Dopamine modulation in the basal ganglia locks the gate to working memory. J. Comput. Neurosci. 20, 153–166 (2006).

    Article  PubMed  Google Scholar 

  195. O’Reilly, R. C. Biologically based computational models of high-level cognition. Science 314, 91–94 (2006).

    Article  PubMed  CAS  Google Scholar 

  196. Ciresan, D., Meier, U. & Schmidhuber, J. Multi-column deep neural networks for image classification. In Proc. 2012 IEEE Conference on Computer Vision and Pattern Recognition 3642–3649 (IEEE, 2012).

  197. Schmidhuber, J. Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015).

    Article  PubMed  Google Scholar 

  198. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    Article  CAS  Google Scholar 

  199. Zhou, B., Bau, D., Oliva, A. & Torralba, A. Interpreting deep visual representations via network dissection. IEEE Transactions on Pattern Analysis and Machine Intelligence 41, 2131–2145 (2019).

    Article  PubMed  Google Scholar 

  200. Richards, B. A. et al. A deep learning framework for neuroscience. Nat. Neurosci. 22, 1761–1770 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  201. Körding, K. P. & König, P. Supervised and unsupervised learning with two sites of synaptic integration. J Comput Neurosci 11, 207–215 (2001).

    Article  PubMed  Google Scholar 

  202. Guerguiev, J., Lillicrap, T. P. & Richards, B. A. Towards deep learning with segregated dendrites. eLife 6, e22901 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  203. Scellier, B. & Bengio, Y. Equilibrium propagation: bridging the gap between energy-based models and backpropagation. Front. Comput. Neurosci. 11, 24 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  204. Roelfsema, P. E. & van Ooyen, A. Attention-gated reinforcement learning of internal representations for classification. Neural Comput. 17, 2176–2214 (2005).

    Article  PubMed  Google Scholar 

  205. Crick, F. The recent excitement about neural networks. Nature 337, 129–132 (1989).

    Article  CAS  PubMed  Google Scholar 

  206. Lillicrap, T. P., Santoro, A., Marris, L., Akerman, C. J. & Hinton, G. Backpropagation and the brain. Nat. Rev. Neurosci. 21, 335–346 (2020).

    Article  CAS  PubMed  Google Scholar 

  207. Szegedy, C., Ioffe, S., Vanhoucke, V. & Alemi, A. A. Inception-v4, inception-ResNet and the impact of residual connections on learning. In Proc. of the Thirty-First AAAI Conference on Artificial Intelligence 4278–4284 (2017).

  208. Khaligh-Razavi, S. M. & Kriegeskorte, N. Deep supervised, but not unsupervised, models may explain IT cortical representation. PLoS Comput. Biol. 10, e1003915 (2014).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  209. Güçlü, U. & Gerven, M. A. J. V. Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream. J. Neurosci. 35, 10005–10014 (2015).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  210. Yamins, D. L. K. et al. Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proc. Natl Acad. Sci. USA 111, 8619–8624 (2014).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  211. Kriegeskorte, N. Deep neural networks: a new framework for modeling biological vision and brain information processing. Ann. Rev. Vis. Sci. 1, 417–446 (2015).

    Article  Google Scholar 

  212. Yamins, D. L. K. & DiCarlo, J. J. Using goal-driven deep learning models to understand sensory cortex. Nat. Neurosci. 19, 356–365 (2016).

    Article  CAS  PubMed  Google Scholar 

  213. Baker, N., Lu, H., Erlikhman, G. & Kellman, P. J. Deep convolutional networks do not classify based on global object shape. PLoS Comput. Biol. 14, e1006613 (2018).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  214. Brendel, W. & Bethge, M. Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet. In Proc. 7th International Conference on Learning Representations (OpenReview.net, 2019).

  215. He, K., Gkioxari, G., Dollar, P. & Girshick, R. Mask R-CNN. In Proc. IEEE International Conference on Computer Vision 2017 2980–2988 (IEEE, 2017).

  216. Pinheiro, P. O., Collobert, R. & Dollar, P. Learning to segment object candidates. In Proc. Advances in Neural Information Processing Systems 28 (eds Cortes, C. et al.) 1990–1998 (Curran Associates, 2015).

  217. Luo, W. et al. Multiple object tracking: a literature review. Artificial Intelligence 293, 103448 (2021).

    Article  Google Scholar 

  218. Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 580–587 (IEEE, 2014).

  219. Bisley, J. W. & Goldberg, M. E. Attention, intention, and priority in the parietal lobe. Ann. Rev. Neurosci. 33, 1–21 (2010).

    Article  CAS  PubMed  Google Scholar 

  220. Burgess, C. P. et al. MONet: unsupervised scene decomposition and representation. Preprint at http://arxiv.org/abs/1901.11390 (2019).

  221. Locatello, F. et al. Object-centric learning with slot attention. In Proc. Advances in Neural Information Processing Systems 33 (eds. Larochelle, H. et al.) 11525–11538 (Curran Associates, 2020).

  222. Eslami, S. M. A. et al. Attend, infer, repeat: fast scene understanding with generative models. In Proc. Advances in Neural Information Processing Systems 29 (eds. Lee, D. et al.) (Curran Associates, 2016).

  223. Wu, J., Lu, E., Kohli, P., Freeman, B. & Tenenbaum, J. Learning to see physics via visual de-animation. In Proc. Advances in Neural Information Processing Systems 30 (eds. Guyon, I. et al.) (Curran Associates, 2017).

  224. Spoerer, C. J., McClure, P. & Kriegeskorte, N. Recurrent convolutional neural networks: a better model of biological object recognition. Front. Psychology 8, 1551 (2017).

    Article  Google Scholar 

  225. Kubilius, J. et al. Brain-like object recognition with high-performing shallow recurrent ANNs. In Proc. Advances in Neural Information Processing Systems 32 (eds. Wallach, H. et al.) (Curran Associates, 2019).

  226. Kietzmann, T. C. et al. Recurrence is required to capture the representational dynamics of the human visual system. Proc. Natl Acad. Sci. USA 116, 21854–21863 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  227. Spoerer, C. J., Kietzmann, T. C., Mehrer, J., Charest, I. & Kriegeskorte, N. Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision. PLoS Comput. Biol. 16, e1008215 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  228. O’Reilly, R. C., Wyatte, D., Herd, S., Mingus, B. & Jilk, D. J. Recurrent processing during object recognition. Front. Psychol. 4, 124 (2013).

    Article  PubMed  PubMed Central  Google Scholar 

  229. Wyatte, D., Jilk, D. J. & O’Reilly, R. C. Early recurrent feedback facilitates visual object recognition under challenging conditions. Front. Psychol. 5, 674 (2014).

    Article  PubMed  PubMed Central  Google Scholar 

  230. Linsley, D., Kim, J. & Serre, T. Sample-efficient image segmentation through recurrence. Preprint at https://arxiv.org/abs/1811.11356v3 (2018).

  231. Engelcke, M., Kosiorek, A. R., Jones, O. P. & Posner, I. GENESIS: generative scene inference and sampling witho object-centric latent representations. In Proc. 8th International Conference on Learning Representations (OpenReview.net, 2020).

  232. Steenkiste, S. van, Chang, M., Greff, K. & Schmidhuber, J. Relational neural expectation maximization: unsupervised discovery of objects and their interactions. In Proc. 6th International Conference on Learning Representations (OpenReview.net, 2018).

  233. Greff, K. et al. Multi-object representation learning with iterative variational inference. In Proc. 36th International Conference on Machine Learning (eds Chaudhuri, K. & Salakhutdinov, R.) 2424–2433 (PLMR, 2019).

  234. Swan, G. & Wyble, B. The binding pool: a model of shared neural resources for distinct items in visual working memory. Atten. Percept. Psychophys. 76, 2136–2157 (2014).

    Article  PubMed  Google Scholar 

  235. Schneegans, S. & Bays, P. M. Neural architecture for feature binding in visual working memory. J. Neurosci. 37, 3913–3925 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  236. Matthey, L., Bays, P. M. & Dayan, P. A probabilistic palimpsest model of visual short-term memory. PLoS Comput. Biol. 11, e1004003 (2015).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  237. Sabour, S., Frosst, N. & Hinton, G. E. Dynamic routing between capsules. In Proc. Advances in Neural Information Processing Systems 30 (eds. Guyon, I. et al.) (Curran Associates, 2017).

  238. Xu, Z. et al. Unsupervised discovery of parts, structure, and dynamics. In Proc. 7th International Conference on Learning Representations (OpenReview.net, 2019).

  239. Kosiorek, A., Sabour, S., Teh, Y. W. & Hinton, G. E. Stacked capsule autoencoders. In Proc. Advances in Neural Information Processing Systems 32 (eds. Wallach, H. et al.) (Curran Associates, 2019).

  240. Pelli, D. G. & Tillman, K. A. The uncrowded window of object recognition. Nat. Neurosci. 11, 1129–1135 (2008).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  241. Sayim, B., Westheimer, G. & Herzog, M. Gestalt factors modulate basic spatial vision. Psychol. Sci. 21, 641–644 (2010).

    Article  CAS  PubMed  Google Scholar 

  242. Doerig, A., Schmittwilken, L., Sayim, B., Manassi, M. & Herzog, M. H. Capsule networks as recurrent models of grouping and segmentation. PLoS Computational Biology 16, 1–19 (2020).

    Article  CAS  Google Scholar 

  243. Battaglia, P. W. et al. Relational inductive biases, deep learning, and graph networks. Preprint at http://arxiv.org/abs/1806.01261 (2018).

  244. Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M. & Monfardini, G. The graph neural network model. IEEE Trans. Neural Netw. 20, 61–80 (2009).

    Article  PubMed  Google Scholar 

  245. Hsieh, J.-T., Liu, B., Huang, D.-A., Fei-Fei, L. F. & Niebles, J. C. Learning to decompose and disentangle representations for video prediction. In Proc. Advances in Neural Information Processing Systems 31 (eds. Bengio, S. et al.) 515–524 (Curran Associates, 2018).

  246. Whittington, J. C. R. et al. The Tolman-Eichenbaum machine: unifying space and relational memory through generalization in the hippocampal formation. Cell 183, 1249–1263 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  247. Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction (MIT press, 2018).

  248. Botvinick, M. et al. Reinforcement learning, fast and slow. Trends Cogn. Sci. 23, 408–422 (2019).

    Article  PubMed  Google Scholar 

  249. LeCun, Y. The power and limits of deep learning. Res. Technol. Manage. 61, 22–27 (2018).

    Article  Google Scholar 

  250. Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. In Proc. 2nd International Conference on Learning Representations (eds. Bengio, Y. & LeCun, Y.) (openreview.net, 2014).

  251. Rezende, D. J., Mohamed, S. & Wierstra, D. Stochastic backpropagation and approximate inference in deep generative models. In Proc. 31st International Conference on Machine Learning 32 (eds. Xing, E. P. & Jebara, T.)1278–1286 (PMLR, 2014).

  252. Goodfellow, I. et al. Generative adversarial nets. In Proc. Advances in Neural Information Processing Systems 27 (eds. Ghahramani, Z. et al.) (Curran Associates, 2014).

  253. Weis, M. A. et al. Unmasking the inductive biases of unsupervised object representations for video sequences. Preprint at http://arxiv.org/abs/2006.07034 (2020).

  254. Veerapaneni, R. et al. Entity abstraction in visual model-based reinforcement learning. In Proc. Conference on Robot Learning 100 (eds. Kaelbling, L. P. et al.) 1439–1456 (PMLR, 2020).

  255. Watters, N., Tenenbaum, J. & Jazayeri, M. Modular object-oriented games: a task framework for reinforcement learning, psychology, and neuroscience. Preprint at http://arxiv.org/abs/2102.12616 (2021).

  256. Leibo, J. Z. et al. Psychlab: a psychology laboratory for deep reinforcement learning agents. Preprint at http://arxiv.org/abs/1801.08116 (2018).

  257. Deng, J. et al. Imagenet: a large-scale hierarchical image database. In Proc. 2009 IEEE Conference on Computer Vision and Pattern Recognition 248–255 (IEEE, 2009).

  258. Geiger, A., Lenz, P. & Urtasun, R. Are we ready for autonomous driving? The KITTI vision benchmark suite. In Proc. Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2012).

  259. Sullivan, J., Mei, M., Perfors, A., Wojcik, E. & Frank, M. C. SAYCam: a large, longitudinal audiovisual dataset recorded from the infant’s perspective. Open Mind 5, 20–29 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  260. Daw, N. D., Gershman, S. J., Seymour, B., Dayan, P. & Dolan, R. J. Model-based influences on humans’ choices and striatal prediction errors. Neuron 69, 1204–1215 (2011).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  261. Green, D. M., & Swets, J. A. Signal Detection Theory and Psychophysics (Wiley, 1966).

  262. Rust, N. C. & Movshon, J. A. In praise of artifice. Nat. Neurosci. 8, 1647–1650 (2005).

    Article  CAS  PubMed  Google Scholar 

  263. Wu, M. C.-K., David, S. V. & Gallant, J. L. Complete functional characterization of sensory neurons by system identification. Ann. Rev. Neurosci. 29, 477–505 (2006).

    Article  CAS  PubMed  Google Scholar 

  264. Ullman, S. Visual routines. Cognition 18, 97–159 (1984).

    Article  CAS  PubMed  Google Scholar 

  265. Jolicoeur, P., Ullman, S. & Mackay, M. Curve tracing: a possible basic operation in the perception of spatial relations. Mem. Cogn. 14, 129–140 (1986).

    Article  CAS  Google Scholar 

  266. Ballard, D. H., Hayhoe, M. M., Pook, P. K. & Rao, R. P. N. Deictic codes for the embodiment of cognition. Behav. Brain Sci. 20, 723–742 (1997).

    Article  CAS  PubMed  Google Scholar 

  267. Geirhos, R. et al. Generalisation in humans and deep neural networks. In Proc. Advances in Neural Information Processing Systems 31 (eds. Bengio, S. et al.) (Curran Associates, 2018).

  268. Barbu, A. et al. ObjectNet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. In Proc. Advances in Neural Information Processing Systems 32 (eds. Wallach, H. et al.) (Curran Associates, 2019).

  269. Blaser, E., Pylyshyn, Z. W. & Holcombe, A. O. Tracking an object through feature space. Nature 408, 196–199 (2000).

    Article  CAS  PubMed  Google Scholar 

  270. Johansson, G. Visual perception of biological motion and a model for its analysis. Percept. Psychophys. 14, 201–211 (1973).

    Article  Google Scholar 

  271. Schrimpf, M. et al. Integrative benchmarking to advance neurally mechanistic models of human intelligence. Neuron 108, 413–423 (2020).

    Article  CAS  PubMed  Google Scholar 

  272. Judd, T., Durand, F. & Torralba, A. A Benchmark of Computational Models of Saliency to Predict Human Fixations Technical Report (MIT, 2012).

  273. Kümmerer, M., Wallis, T. S. A., Gatys, L. A. & Bethge, M. Understanding low- and high-level contributions to fixation prediction. In Proc. 2017 IEEE International Conference on Computer Vision 4799–4808 (IEEE, 2017).

  274. Ma, W. J. & Peters, B. A neural network walks into a lab: towards using deep nets as models for human behavior. Preprint at http://arxiv.org/abs/2005.02181 (2020).

  275. Peterson, J., Battleday, R., Griffiths, T. & Russakovsky, O. Human uncertainty makes classification more robust. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV) 9616–9625 (IEEE, 2019).

  276. Bakhtin, A., van der Maaten, L., Johnson, J., Gustafson, L. & Girshick, R. PHYRE: a new benchmark for physical reasoning. In Proc. Advances in Neural Information Processing Systems 32 (eds. Wallach, H. et al.) (Curran Associates, 2019).

  277. Yi, K. et al. CLEVRER: collision events for video representation and reasoning. In Proc. 8th International Conference on Learning Representations (OpenReview.net, 2020).

  278. Riochet, R. et al. IntPhys: a framework and benchmark for visual intuitive physics reasoning. CoRR, abs/1803.07616 (2018).

  279. Baradel, F., Neverova, N., Mille, J., Mori, G. & Wolf, C. CoPhy: counterfactual learning of physical dynamics. In Proc. 8th International Conference on Learning Representations (OpenReview.net, 2020).

  280. Girdhar, R. & Ramanan, D. CATER: A diagnostic dataset for compositional actions & temporal reasoning. In Proc. 8th International Conference on Learning Representations (OpenReview.net, 2020).

  281. Allen, K. R., Smith, K. A. & Tenenbaum, J. B. Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning. Proc. Natl Acad. Sci. USA 117, 29302–29310 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  282. Beyret, B. et al. The Animal-AI environment: training and testing animal-like artificial cognition. Preprint at http://arxiv.org/abs/1909.07483 (2019).

  283. Kanizsa, G. Margini quasi-percettivi in campi con stimolazione omogenea. Riv. Psicol. 49, 7–30 (1955).

    Google Scholar 

  284. Kanizsa, G. Amodale ergänzung und ‘erwartungsfehler’ des gestaltpsychologen. Psychol. Forsch. 33, 325–344 (1970).

    Article  CAS  PubMed  Google Scholar 

  285. Eslami, S. M. A. et al. Neural scene representation and rendering. Science 360, 1204–1210 (2018).

    Article  CAS  PubMed  Google Scholar 

  286. Beattie, C. et al. {DeepMind} {Lab}. Preprint at http://arxiv.org/abs/1612.03801 (2016).

  287. Kolve, E. et al. AI2-THOR: an interactive 3D environment for visual AI. Preprint at https://arxiv.org/abs/1712.05474 (2017).

  288. Lin, T.-Y. et al. Microsoft COCO: common objects in context. In Computer Vision—ECCV 2014, Lecture Notes in Computer Science (eds Fleet, D. et al.) 740–755 (Springer, 2014).

  289. Milan, A., Leal-Taixe, L., Reid, I., Roth, S. & Schindler, K. MOT16: a benchmark for multi-object tracking. Preprint at http://arxiv.org/abs/1603.00831 (2016).

  290. Mahler, J. et al. Learning ambidextrous robot grasping policies. Sci. Robot. 4, eaau4984 (2019).

    Article  PubMed  Google Scholar 

  291. Pitkow, X. Exact feature probabilities in images with occlusion. J. Vis. 10, 42 (2010).

    Article  PubMed  Google Scholar 

  292. O’Reilly, R. C., Busby, R. S. & Soto, R. Three forms of binding and their neural substrates: Alternatives to temporal synchrony. In The unity of consciousness: Binding, integration, and dissociation (ed. Cleeremans, A.) 168–190 (Oxford Univ. Press, 2003).

  293. Hummel, J. E. et al. A solution to the binding problem for compositional connectionism. In AAAI Fall Symposium - Technical Report (eds. Levy, S. D. & Gayler, R.) vol. FS-04-03 31–34 (AAAI Press, 2004).

  294. Hinton, G. E., McClelland, J. L. & Rumelhart, D. E. Distributed Representations. In Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations (eds. Rumelhart, D. E. & McClelland, J. L.) 77–109 (MIT Press, 1987).

  295. Treisman, A. Solutions to the binding problem: progress through controversy and convergence. Neuron 24, 105–125 (1999).

    Article  CAS  PubMed  Google Scholar 

  296. Ballard, D. H., Hinton, G. E. & Sejnowski, T. J. Parallel visual computation. Nature 306, 21–26 (1983).

    Article  CAS  PubMed  Google Scholar 

  297. Smolensky, P. Tensor product variable binding and the representation of symbolic structures in connectionist systems. Artif. Int. 46, 159–216 (1990).

    Article  Google Scholar 

  298. Feldman, J. A. Dynamic connections in neural networks. Biol. Cybernet. 46, 27–39 (1982).

    Article  CAS  Google Scholar 

  299. Von Der Malsburg, C. Am I thinking assemblies? Brain Theory 161–176 (1986)

  300. Reynolds, J. H. & Desimone, R. The role of neural mechanisms of attention in solving the binding problem. Neuron 24, 19–29 (1999).

    Article  CAS  PubMed  Google Scholar 

  301. Shadlen, M. N. & Movshon, J. A. Synchrony unbound: a critical evaluation of the temporal binding hypothesis. Neuron 24, 67–77 (1999).

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

B.P. has received funding from the EU Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement no. 841578.

Author information

Authors and Affiliations

Authors

Corresponding authors

Correspondence to Benjamin Peters or Nikolaus Kriegeskorte.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Peters, B., Kriegeskorte, N. Capturing the objects of vision with neural networks. Nat Hum Behav 5, 1127–1144 (2021). https://doi.org/10.1038/s41562-021-01194-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41562-021-01194-6

This article is cited by

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing