{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T05:09:47Z","timestamp":1781068187400,"version":"3.54.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013391","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000}}],"reference-count":90,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Kempner Institute","award":["Kempner Graduate Fellowship"],"award-info":[{"award-number":["Kempner Graduate Fellowship"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF CAREER: BCS-1942438"],"award-info":[{"award-number":["NSF CAREER: BCS-1942438"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF PAC COMP-COG 1946308"],"award-info":[{"award-number":["NSF PAC COMP-COG 1946308"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Deep neural network models provide a powerful experimental platform for exploring core mechanisms underlying human visual perception, such as perceptual grouping and contour integration\u2014the process of linking local edge elements to arrive at a unified perceptual representation of a complete contour. Here, we demonstrate that feedforward convolutional neural networks (CNNs) fine-tuned on contour detection show this human-like capacity, but without relying on mechanisms proposed in prior work, such as lateral connections, recurrence, or top-down feedback. We identified two key properties needed for ImageNet pre-trained, feed-forward models to yield human-like contour integration: first, progressively increasing receptive field structure served as a critical architectural motif to support this capacity; and second, biased fine-tuning for contour-detection specifically for gradual curves (~20\u2009degrees) resulted in human-like sensitivity to curvature. We further demonstrate that fine-tuning ImageNet pretrained models uncovers other hidden human-like capacities in feed-forward networks, including uncrowding (reduced interference from distractors as the number of distractors increases), which is considered a signature of human perceptual grouping. Thus, taken together these results provide a computational existence proof that purely feedforward hierarchical computations are capable of implementing gestalt \u201cgood continuation\u201d and perceptual organization needed for human-like contour-integration and uncrowding. More broadly, these results raise the possibility that in human vision, later stages of processing play a more prominent role in perceptual-organization than implied by theories focused on recurrence and early lateral connections.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013391","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T17:52:46Z","timestamp":1755539566000},"page":"e1013391","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["A feedforward mechanism for human-like contour integration"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3978-7782","authenticated-orcid":true,"given":"Fenil R.","family":"Doshi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Talia","family":"Konkle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George A.","family":"Alvarez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"issue":"2","key":"pcbi.1013391.ref001","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1037\/0033-295X.94.2.115","article-title":"Recognition-by-components: a theory of human image understanding","volume":"94","author":"I Biederman","year":"1987","journal-title":"Psychol Rev"},{"issue":"1","key":"pcbi.1013391.ref002","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/0010-0285(88)90024-2","article-title":"Surface versus edge-based determinants of visual recognition","volume":"20","author":"I Biederman","year":"1988","journal-title":"Cogn Psychol"},{"issue":"1140","key":"pcbi.1013391.ref003","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1098\/rspb.1978.0020","article-title":"Representation and recognition of the spatial organization of three-dimensional shapes","volume":"200","author":"D Marr","year":"1978","journal-title":"Proc R Soc Lond B Biol Sci"},{"issue":"5075","key":"pcbi.1013391.ref004","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1126\/science.1529336","article-title":"Experiencing and perceiving visual surfaces","volume":"257","author":"K Nakayama","year":"1992","journal-title":"Science"},{"key":"pcbi.1013391.ref005","volume-title":"Visual surface representation: A critical link between lower-level and higher-level vision","author":"K Nakayama","year":"1995"},{"key":"pcbi.1013391.ref006","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.3389\/fpsyg.2015.01695","article-title":"Figure-ground organization and the emergence of proto-objects in the visual cortex","volume":"6","author":"R von der Heydt","year":"2015","journal-title":"Front Psychol"},{"key":"pcbi.1013391.ref007","first-page":"161","article-title":"Experimentelle studien uber das sehen von bewegung","volume":"61","author":"M Wertheimer","year":"1912","journal-title":"Zeitschrift fur Psychologie"},{"key":"pcbi.1013391.ref008","article-title":"Gestalt psychology","volume":"31","author":"W K\u00f6hler","year":"1967","journal-title":"Psychologische Forschung"},{"issue":"10","key":"pcbi.1013391.ref009","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1037\/h0072422","article-title":"Perception: an introduction to the Gestalt-Theorie","volume":"19","author":"K Koffka","year":"1922","journal-title":"Psychological Bulletin"},{"key":"pcbi.1013391.ref010","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/BF00410640","article-title":"Untersuchungen zur Lehre von der Gestalt, II. [Investigations in Gestalt Theory: II. Laws of organization in perceptual forms]","volume":"4","author":"M Wertheimer","year":"1923","journal-title":"Psychologische Forschung"},{"key":"pcbi.1013391.ref011","doi-asserted-by":"crossref","DOI":"10.1037\/11496-005","volume-title":"Laws of organization in perceptual forms","author":"M Wertheimer","year":"1938"},{"issue":"2","key":"pcbi.1013391.ref012","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1068\/p7122","article-title":"An early history of the Gestalt factors of organisation","volume":"41","author":"S Vezzani","year":"2012","journal-title":"Perception"},{"issue":"6","key":"pcbi.1013391.ref013","doi-asserted-by":"crossref","first-page":"1172","DOI":"10.1037\/a0029333","article-title":"A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure-ground organization","volume":"138","author":"J Wagemans","year":"2012","journal-title":"Psychol Bull"},{"key":"pcbi.1013391.ref014","doi-asserted-by":"crossref","DOI":"10.4324\/9781315009247","volume-title":"A source book of Gestalt psychology","author":"WD Ellis","year":"2013"},{"issue":"2","key":"pcbi.1013391.ref015","doi-asserted-by":"crossref","first-page":"182","DOI":"10.3758\/BF03200772","article-title":"The perceptual organization of dot lattices","volume":"1","author":"M Kubovy","year":"1994","journal-title":"Psychon Bull Rev"},{"key":"pcbi.1013391.ref016","article-title":"Brightness and proximity factors in grouping","author":"J Hochberg","year":"1960","journal-title":"Percept Mot Skills"},{"issue":"4","key":"pcbi.1013391.ref017","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1068\/p270417","article-title":"Grouping by proximity or similarity? Competition between the Gestalt principles in vision","volume":"27","author":"PT Quinlan","year":"1998","journal-title":"Perception"},{"key":"pcbi.1013391.ref018","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1037\/h0046557","article-title":"Grouping based on phenomenal proximity","volume":"67","author":"I Rock","year":"1964","journal-title":"J Exp Psychol"},{"key":"pcbi.1013391.ref019","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, 2012. 25."},{"issue":"3","key":"pcbi.1013391.ref020","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"O Russakovsky","year":"2015","journal-title":"Int J Comput Vis"},{"issue":"4","key":"pcbi.1013391.ref021","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004896","article-title":"Deep Neural Networks as a Computational Model for Human Shape Sensitivity","volume":"12","author":"J Kubilius","year":"2016","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1013391.ref022","unstructured":"Ritter S, Barrett DG, Santoro A, Botvinick MM. Cognitive psychology for deep neural networks: A shape bias case study. In: International conference on machine learning, 2017. 2940\u20139."},{"key":"pcbi.1013391.ref023","volume-title":"Learning inductive biases with simple neural networks","author":"R Feinman","year":"2018"},{"issue":"8","key":"pcbi.1013391.ref024","doi-asserted-by":"crossref","first-page":"2648","DOI":"10.1111\/cogs.12670","article-title":"Evaluating (and Improving) the Correspondence Between Deep Neural Networks and Human Representations","volume":"42","author":"JC Peterson","year":"2018","journal-title":"Cogn Sci"},{"issue":"1","key":"pcbi.1013391.ref025","doi-asserted-by":"crossref","first-page":"5418","DOI":"10.1038\/s41467-020-18946-z","article-title":"Capturing human categorization of natural images by combining deep networks and cognitive models","volume":"11","author":"RM Battleday","year":"2020","journal-title":"Nat Commun"},{"issue":"11","key":"pcbi.1013391.ref026","article-title":"Deep supervised, but not unsupervised, models may explain IT cortical representation","volume":"10","author":"S-M Khaligh-Razavi","year":"2014","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1013391.ref027","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1038\/nn.4244","article-title":"Using goal-driven deep learning models to understand sensory cortex","volume":"19","author":"DL Yamins","year":"2016","journal-title":"Nature Neuroscience"},{"issue":"27","key":"pcbi.1013391.ref028","doi-asserted-by":"crossref","first-page":"10005","DOI":"10.1523\/JNEUROSCI.5023-14.2015","article-title":"Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream","volume":"35","author":"U G\u00fc\u00e7l\u00fc","year":"2015","journal-title":"J Neurosci"},{"key":"pcbi.1013391.ref029","article-title":"Brain-score: Which artificial neural network for object recognition is most brain-like?","author":"M Schrimpf","year":"2018","journal-title":"BioRxiv"},{"issue":"33","key":"pcbi.1013391.ref030","doi-asserted-by":"crossref","first-page":"7255","DOI":"10.1523\/JNEUROSCI.0388-18.2018","article-title":"Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks","volume":"38","author":"R Rajalingham","year":"2018","journal-title":"J Neurosci"},{"issue":"1","key":"pcbi.1013391.ref031","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1038\/s41467-022-28091-4","article-title":"A self-supervised domain-general learning framework for human ventral stream representation","volume":"13","author":"T Konkle","year":"2022","journal-title":"Nat Commun"},{"key":"pcbi.1013391.ref032","doi-asserted-by":"crossref","first-page":"4082","DOI":"10.1167\/jov.22.14.4082","article-title":"Isolating global form processing using shape metamers","volume":"22","author":"G Alvarez","year":"2022","journal-title":"Journal of Vision"},{"issue":"12","key":"pcbi.1013391.ref033","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1006613","article-title":"Deep convolutional networks do not classify based on global object shape","volume":"14","author":"N Baker","year":"2018","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1013391.ref034","volume-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"R Geirhos","year":"2018"},{"key":"pcbi.1013391.ref035","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.visres.2020.04.013","article-title":"Hiding a plane with a pixel: examining shape-bias in CNNs and the benefit of building in biological constraints","volume":"174","author":"G Malhotra","year":"2020","journal-title":"Vision Res"},{"issue":"12","key":"pcbi.1013391.ref036","doi-asserted-by":"crossref","first-page":"3380","DOI":"10.1037\/xge0001440","article-title":"Human shape representations are not an emergent property of learning to classify objects","volume":"152","author":"G Malhotra","year":"2023","journal-title":"J Exp Psychol Gen"},{"issue":"10","key":"pcbi.1013391.ref037","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1167\/jov.22.10.11","article-title":"Can deep convolutional neural networks support relational reasoning in the same-different task?","volume":"22","author":"G Puebla","year":"2022","journal-title":"J Vis"},{"key":"pcbi.1013391.ref038","doi-asserted-by":"crossref","first-page":"961595","DOI":"10.3389\/frai.2022.961595","article-title":"Configural relations in humans and deep convolutional neural networks","volume":"5","author":"N Baker","year":"2023","journal-title":"Front Artif Intell"},{"issue":"1","key":"pcbi.1013391.ref039","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1038\/s41467-021-22078-3","article-title":"Qualitative similarities and differences in visual object representations between brains and deep networks","volume":"12","author":"G Jacob","year":"2021","journal-title":"Nat Commun"},{"key":"pcbi.1013391.ref040","article-title":"Deep problems with neural network models of human vision","author":"JS Bowers","year":"2022","journal-title":"Behavioral and Brain Sciences"},{"issue":"3","key":"pcbi.1013391.ref041","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1007\/s42113-023-00169-2","article-title":"Mixed Evidence for Gestalt Grouping in Deep Neural Networks","volume":"6","author":"V Biscione","year":"2023","journal-title":"Comput Brain Behav"},{"key":"pcbi.1013391.ref042","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.visres.2019.12.006","article-title":"Crowding reveals fundamental differences in local vs. global processing in humans and machines","volume":"167","author":"A Doerig","year":"2020","journal-title":"Vision Research"},{"key":"pcbi.1013391.ref043","first-page":"9995","article-title":"What shapes feature representations? Exploring datasets, architectures, and training","volume":"33","author":"K Hermann","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"11","key":"pcbi.1013391.ref044","doi-asserted-by":"crossref","first-page":"1761","DOI":"10.1038\/s41593-019-0520-2","article-title":"A deep learning framework for neuroscience","volume":"22","author":"BA Richards","year":"2019","journal-title":"Nat Neurosci"},{"issue":"7","key":"pcbi.1013391.ref045","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1008017","article-title":"Capsule networks as recurrent models of grouping and segmentation","volume":"16","author":"A Doerig","year":"2020","journal-title":"PLoS Comput Biol"},{"issue":"4","key":"pcbi.1013391.ref046","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1167\/2.4.5","article-title":"Ecological statistics of Gestalt laws for the perceptual organization of contours","volume":"2","author":"JH Elder","year":"2002","journal-title":"J Vis"},{"issue":"6","key":"pcbi.1013391.ref047","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1016\/S0042-6989(00)00277-7","article-title":"Edge co-occurrence in natural images predicts contour grouping performance","volume":"41","author":"WS Geisler","year":"2001","journal-title":"Vision Res"},{"issue":"2","key":"pcbi.1013391.ref048","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/0042-6989(93)90156-Q","article-title":"Contour integration by the human visual system: evidence for a local \u201cassociation field\u201d","volume":"33","author":"DJ Field","year":"1993","journal-title":"Vision Res"},{"issue":"1","key":"pcbi.1013391.ref049","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1113\/jphysiol.1968.sp008455","article-title":"Receptive fields and functional architecture of monkey striate cortex","volume":"195","author":"DH Hubel","year":"1968","journal-title":"J Physiol"},{"issue":"12","key":"pcbi.1013391.ref050","doi-asserted-by":"crossref","first-page":"2379","DOI":"10.1364\/JOSAA.4.002379","article-title":"Relations between the statistics of natural images and the response properties of cortical cells","volume":"4","author":"DJ Field","year":"1987","journal-title":"J Opt Soc Am A"},{"issue":"6","key":"pcbi.1013391.ref051","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1109\/TPAMI.2003.1201818","article-title":"Contour grouping with prior models","volume":"25","author":"JH Elder","year":"2003","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"issue":"4","key":"pcbi.1013391.ref052","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1016\/0896-6273(95)90175-2","article-title":"Improvement in visual sensitivity by changes in local context: parallel studies in human observers and in V1 of alert monkeys","volume":"15","author":"MK Kapadia","year":"1995","journal-title":"Neuron"},{"issue":"8","key":"pcbi.1013391.ref053","doi-asserted-by":"crossref","DOI":"10.1167\/8.8.8","article-title":"A recurrent model of contour integration in primary visual cortex","volume":"8","author":"T Hansen","year":"2008","journal-title":"J Vis"},{"issue":"4","key":"pcbi.1013391.ref054","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1162\/089976698300017557","article-title":"A neural model of contour integration in the primary visual cortex","volume":"10","author":"Z Li","year":"1998","journal-title":"Neural Comput"},{"key":"pcbi.1013391.ref055","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1146\/annurev.neuro.29.051605.112939","article-title":"Cortical algorithms for perceptual grouping","volume":"29","author":"PR Roelfsema","year":"2006","journal-title":"Annu Rev Neurosci"},{"issue":"43","key":"pcbi.1013391.ref056","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.1317019110","article-title":"Network model of top-down influences on local gain and contextual interactions in visual cortex","volume":"110","author":"V Pi\u00ebch","year":"2013","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pcbi.1013391.ref057","doi-asserted-by":"crossref","unstructured":"Linsley D, Kim J, Veerabadran V, Windolf C, Serre T. Learning long-range spatial dependencies with horizontal gated recurrent units. In: Advances in neural information processing systems, 2018. 31.","DOI":"10.32470\/CCN.2018.1116-0"},{"key":"pcbi.1013391.ref058","volume-title":"V1Net: A computational model of cortical horizontal connections","author":"V Veerabadran","year":"2019"},{"key":"pcbi.1013391.ref059","unstructured":"Linsley D, Kim J, Ashok A, Serre T. Recurrent neural circuits for contour detection. 2020."},{"key":"pcbi.1013391.ref060","unstructured":"Khan S, Wong A, Tripp BP. Task-driven learning of contour integration responses in a V1 model. In: NeurIPS 2020 Workshop SVRHM, 2020."},{"issue":"1","key":"pcbi.1013391.ref061","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1008629","article-title":"Sparse deep predictive coding captures contour integration capabilities of the early visual system","volume":"17","author":"V Boutin","year":"2021","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1013391.ref062","volume-title":"Approximating cnns with bag-of-local-features models works surprisingly well on imagenet","author":"W Brendel","year":"2019"},{"key":"pcbi.1013391.ref063","unstructured":"Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M. Striving for simplicity: The all convolutional net. In: 2014."},{"key":"pcbi.1013391.ref064","volume-title":"Signal detection theory and psychophysics","author":"DM Green","year":"1966"},{"key":"pcbi.1013391.ref065","volume-title":"Decision-margin consistency: a principled metric for human and machine performance alignment","author":"GA Alvarez","year":"2024"},{"key":"pcbi.1013391.ref066","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: 2016. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"key":"pcbi.1013391.ref067","author":"A Dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint"},{"key":"pcbi.1013391.ref068","author":"A Steiner","year":"2021","journal-title":"How to train your vit? Data, augmentation, and regularization in vision transformers"},{"key":"pcbi.1013391.ref069","volume-title":"Pytorch image models","author":"R Wightman","year":"2019"},{"issue":"1","key":"pcbi.1013391.ref070","doi-asserted-by":"crossref","first-page":"5725","DOI":"10.1038\/s41467-020-19632-w","article-title":"Individual differences among deep neural network models","volume":"11","author":"J Mehrer","year":"2020","journal-title":"Nat Commun"},{"key":"pcbi.1013391.ref071","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.visres.2015.05.021","article-title":"A unified account of tilt illusions, association fields, and contour detection based on elastica","volume":"126","author":"SW Keemink","year":"2016","journal-title":"Vision Res"},{"issue":"4","key":"pcbi.1013391.ref072","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1037\/0033-295X.107.4.677","article-title":"Perceptual organization of two-dimensional patterns","volume":"107","author":"WS Geisler","year":"2000","journal-title":"Psychol Rev"},{"issue":"6","key":"pcbi.1013391.ref073","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1364\/JOSAA.15.001486","article-title":"Spatial-frequency tuning of visual contour integration","volume":"15","author":"SC Dakin","year":"1998","journal-title":"J Opt Soc Am A Opt Image Sci Vis"},{"issue":"3","key":"pcbi.1013391.ref074","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1163\/156856899X00184","article-title":"Contour integration and scale combination processes in visual edge detection","volume":"12","author":"SC Dakin","year":"1999","journal-title":"Spat Vis"},{"issue":"6660","key":"pcbi.1013391.ref075","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1038\/37593","article-title":"Absence of contour linking in peripheral vision","volume":"390","author":"RF Hess","year":"1997","journal-title":"Nature"},{"issue":"1","key":"pcbi.1013391.ref076","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1163\/156856800741018","article-title":"The roles of polarity and symmetry in the perceptual grouping of contour fragments","volume":"13","author":"DJ Field","year":"2000","journal-title":"Spat Vis"},{"issue":"12","key":"pcbi.1013391.ref077","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1016\/0042-6989(94)00261-J","article-title":"Contour integration across depth","volume":"35","author":"RF Hess","year":"1995","journal-title":"Vision Res"},{"key":"pcbi.1013391.ref078","doi-asserted-by":"crossref","unstructured":"Wang W, Neumann U. Depth-aware cnn for rgb-d segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), 2018. 135\u201350.","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"pcbi.1013391.ref079","volume-title":"Dinov2: Learning robust visual features without supervision","author":"M Oquab","year":"2023"},{"key":"pcbi.1013391.ref080","volume-title":"Billion-scale semi-supervised learning for image classification","author":"IZ Yalniz","year":"2019"},{"key":"pcbi.1013391.ref081","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1162\/opmi_a_00039","article-title":"SAYCam: A Large, Longitudinal Audiovisual Dataset Recorded From the Infant\u2019s Perspective","volume":"5","author":"J Sullivan","year":"2021","journal-title":"Open Mind (Camb)"},{"key":"pcbi.1013391.ref082","unstructured":"Grauman K, Westbury A, Byrne E, Chavis Z, Furnari A, Girdhar R. Ego4d: Around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 18995\u20139012."},{"key":"pcbi.1013391.ref083","volume-title":"Pre-training on high-quality natural image data reduces DCNN texture bias","author":"N Muller","year":"2023"},{"key":"pcbi.1013391.ref084","author":"R Geirhos","year":"2020","journal-title":"On the surprising similarities between supervised and self-supervised models. arXiv preprint"},{"key":"pcbi.1013391.ref085","first-page":"23885","volume":"34","author":"R Geirhos","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pcbi.1013391.ref086","doi-asserted-by":"crossref","unstructured":"Doshi FR, T K, Alvarez GA. Quantifying the Quality of Shape and Texture Representations in Deep Neural Network Models. In: 2024.","DOI":"10.1167\/jov.24.10.1263"},{"issue":"16","key":"pcbi.1013391.ref087","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2023123118","article-title":"Sensitivity to geometric shape regularity in humans and baboons: A putative signature of human singularity","volume":"118","author":"M Sabl\u00e9-Meyer","year":"2021","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pcbi.1013391.ref088","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780199936533.001.0001","volume-title":"Vision and the visual system","author":"PH Schiller","year":"2015"},{"key":"pcbi.1013391.ref089","doi-asserted-by":"crossref","DOI":"10.1101\/511535","volume-title":"A unified theory of early visual representations from retina to cortex through anatomically constrained deep CNNs","author":"J Lindsey","year":"2019"},{"key":"pcbi.1013391.ref090","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"A Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013391","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:02:33Z","timestamp":1755799353000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013391"}},"subtitle":[],"editor":[{"given":"Daniele","family":"Marinazzo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"references-count":90,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013391","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1013391","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,18]]}}}