{"pk":27868,"title":"Same-different problems strain covolutional neural networks","subtitle":null,"abstract":"The robust and efficient recognition of visual relations in im-ages is a hallmark of biological vision. We argue that, de-spite recent progress in visual recognition, modern machinevision algorithms are severely limited in their ability to learnvisual relations. Through controlled experiments, we demon-strate that visual-relation problems strain convolutional neuralnetworks (CNNs). The networks eventually break altogetherwhen rote memorization becomes impossible, as when intra-class variability exceeds network capacity. Motivated by thecomparable success of biological vision, we argue that feed-back mechanisms including attention and perceptual groupingmay be the key computational components underlying abstractvisual reasoning.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"Visual relations"},{"word":"Convolutional Neural Networks"},{"word":"Deep learning"},{"word":"Visual attentino"},{"word":"Perceptual Grouping"}],"section":"Publication-based-Talks","is_remote":true,"remote_url":"https://escholarship.org/uc/item/9zz2g6g1","frozenauthors":[{"first_name":"Mathew","middle_name":"","last_name":"Ricci","name_suffix":"","institution":"Brown","department":""},{"first_name":"Junkyung","middle_name":"","last_name":"Kim","name_suffix":"","institution":"Brown","department":""},{"first_name":"Thomas","middle_name":"","last_name":"Serre","name_suffix":"","institution":"Brown","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2018-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/27868/galley/17506/download/"}]}