{"pk":28797,"title":"The contrasting roles of shape in human vision and convolutional neural networks","subtitle":null,"abstract":"Convolutional neural networks (CNNs) were inspired by hu-man vision and, in some settings, achieve a performance com-parable to human object recognition. This has lead to the spec-ulation that both systems use similar mechanisms to performrecognition. In this study, we conducted a series of simulationsthat indicate that there is a fundamental difference between hu-man vision and vanilla CNNs: while object recognition in hu-mans relies on analysing shape, these CNNs do not have sucha shape-bias. We teased apart the type of features selectedby the model by modifying the CIFAR-10 dataset so that, inaddition to containing objects with shape, the images concur-rently contained non-shape features, such as a noise-like mask.When trained on these modified set of images, the model didnot show any bias towards selecting shapes as features. In-stead it relied on whichever feature allowed it to perform thebest prediction – even when this feature was a noise-like maskor a single predictive pixel amongst 50176 pixels.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Papers with Poster Presentations","is_remote":true,"remote_url":"https://escholarship.org/uc/item/12g3p0hn","frozenauthors":[{"first_name":"Gaurav","middle_name":"","last_name":"Malhotra","name_suffix":"","institution":"University of Bristol","department":""},{"first_name":"Jeffrey","middle_name":"","last_name":"Bowers","name_suffix":"","institution":"University of Bristol","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2019-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/28797/galley/18668/download/"}]}