{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T05:16:29Z","timestamp":1772774189519,"version":"3.50.1"},"reference-count":28,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:00:00Z","timestamp":1698192000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["IIS-2107409, CAREER-2144956, BCS-2120610"],"award-info":[{"award-number":["IIS-2107409, CAREER-2144956, BCS-2120610"]}]},{"name":"NIH","award":["1R21EY033182-01A1"],"award-info":[{"award-number":["1R21EY033182-01A1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Appl. Percept."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"<jats:p>Depth estimation is fundamental to 3D perception, and humans are known to have biased estimates of depth. This study investigates whether convolutional neural networks (CNNs) can be biased when predicting the sign of curvature and depth of surfaces of textured surfaces under different viewing conditions (field of view) and surface parameters (slant and texture irregularity). This hypothesis is drawn from the idea that texture gradients described by local neighborhoods\u2014a cue identified in human vision literature\u2014are also representable within convolutional neural networks. To this end, we trained both unsupervised and supervised CNN models on the renderings of slanted surfaces with random Polka dot patterns and analyzed their internal latent representations. The results show that the unsupervised models have similar prediction biases as humans across all experiments, while supervised CNN models do not exhibit similar biases. The latent spaces of the unsupervised models can be linearly separated into axes representing field of view and optical slant. For supervised models, this ability varies substantially with model architecture and the kind of supervision (continuous slant vs.\u00a0sign of slant). Even though this study says nothing of any shared mechanism, these findings suggest that unsupervised CNN models can share similar predictions to the human visual system. Code: github.com\/brownvc\/Slant-CNN-Biases.<\/jats:p>","DOI":"10.1145\/3613451","type":"journal-article","created":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T08:52:49Z","timestamp":1691225569000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["On Human-like Biases in Convolutional Neural Networks for the Perception of Slant from Texture"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2737-4689","authenticated-orcid":false,"given":"Yuanhao","family":"Wang","sequence":"first","affiliation":[{"name":"Brown University Department of Computer Science, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8187-4970","authenticated-orcid":false,"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Brown University Department of Computer Science, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6000-1617","authenticated-orcid":false,"given":"Celine","family":"Aubuchon","sequence":"additional","affiliation":[{"name":"Brown University Department of Cognitive, Linguistic, and Psychological Sciences, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3775-5197","authenticated-orcid":false,"given":"Jovan","family":"Kemp","sequence":"additional","affiliation":[{"name":"Brown University Department of Cognitive, Linguistic, and Psychological Sciences, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5510-0397","authenticated-orcid":false,"given":"Fulvio","family":"Domini","sequence":"additional","affiliation":[{"name":"Brown University Department of Cognitive, Linguistic, and Psychological Sciences, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2218-2899","authenticated-orcid":false,"given":"James","family":"Tompkin","sequence":"additional","affiliation":[{"name":"Brown University Department of Computer Science, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,25]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2021.107961"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2003.08.007"},{"key":"e_1_3_2_4_1","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos Robert","year":"2018","unstructured":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, and Wieland Brendel. 2018. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018).","journal-title":"arXiv preprint arXiv:1811.12231"},{"key":"e_1_3_2_5_1","doi-asserted-by":"crossref","unstructured":"James J. Gibson. 1950a. The Perception of the Visual World . (1950).","DOI":"10.2307\/1418003"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.2307\/1418003"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_8_1","article-title":"Shape or texture: Understanding discriminative features in CNNs","author":"Islam Md. Amirul","year":"2021","unstructured":"Md. Amirul Islam, Matthew Kowal, Patrick Esser, Sen Jia, Bjorn Ommer, Konstantinos G. Derpanis, and Neil Bruce. 2021. Shape or texture: Understanding discriminative features in CNNs. arXiv preprint arXiv:2101.11604 (2021).","journal-title":"arXiv preprint arXiv:2101.11604"},{"key":"e_1_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/0042-6989(91)90056-B"},{"key":"e_1_3_2_10_1","article-title":"Auto-encoding variational Bayes","author":"Kingma Diederik P.","year":"2013","unstructured":"Diederik P. Kingma and Max Welling. 2013. Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013).","journal-title":"arXiv preprint arXiv:1312.6114"},{"key":"e_1_3_2_11_1","article-title":"Brain-like object recognition with high-performing shallow recurrent ANNs","volume":"32","author":"Kubilius Jonas","year":"2019","unstructured":"Jonas Kubilius, Martin Schrimpf, Kohitij Kar, Rishi Rajalingham, Ha Hong, Najib Majaj, Elias Issa, Pouya Bashivan, Jonathan Prescott-Roy, Kailyn Schmidt, et\u00a0al. 2019. Brain-like object recognition with high-performing shallow recurrent ANNs. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2014.10.036"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/jocn_a_01544"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2004.03.024"},{"key":"e_1_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007958829620"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.2307\/2344614"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003553"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.04.005"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2004.01.013"},{"key":"e_1_3_2_21_1","first-page":"407007","article-title":"Brain-score: Which artificial neural network for object recognition is most brain-like?","author":"Schrimpf Martin","year":"2018","unstructured":"Martin Schrimpf, Jonas Kubilius, Ha Hong, Najib J. Majaj, Rishi Rajalingham, Elias B. Issa, Kohitij Kar, Pouya Bashivan, Jonathan Prescott-Roy, Franziska Geiger, Kailyn Schmidt, Daniel L. K. Yamins, and James J. DiCarlo. 2018. Brain-score: Which artificial neural network for object recognition is most brain-like? BioRxiv (2018), 407007.","journal-title":"BioRxiv"},{"key":"e_1_3_2_22_1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-021-01097-6"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2005.01.003"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1167\/7.12.9"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1167\/5.10.7"},{"key":"e_1_3_2_27_1","article-title":"Publisher correction: Limits to visual representational correspondence between convolutional neural networks and the human brain","volume":"12","author":"Xu Yaoda","year":"2021","unstructured":"Yaoda Xu and Maryam Vaziri-Pashkam. 2021. Publisher correction: Limits to visual representational correspondence between convolutional neural networks and the human brain. Nature Communications 12 (2021).","journal-title":"Nature Communications"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01244"},{"key":"e_1_3_2_29_1","volume-title":"International Conference on Machine Learning","author":"Zhang Richard","year":"2019","unstructured":"Richard Zhang. 2019. Making convolutional networks shift-invariant again. In International Conference on Machine Learning."}],"container-title":["ACM Transactions on Applied Perception"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613451","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:30Z","timestamp":1750178190000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,25]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3613451"],"URL":"https:\/\/doi.org\/10.1145\/3613451","relation":{},"ISSN":["1544-3558","1544-3965"],"issn-type":[{"value":"1544-3558","type":"print"},{"value":"1544-3965","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,25]]},"assertion":[{"value":"2023-07-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-26","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}