{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adapting-deep-network-features-to-capture","title":"Adapting Deep Network Features to Capture Psychological Representations","arxiv_id":"1608.02164","date":"2016-08-06","proceeding":null,"authors":["Joshua C. Peterson","Joshua T. Abbott","Thomas L. Griffiths"],"abstract":"Deep neural networks have become increasingly successful at solving classic\nperception problems such as object recognition, semantic segmentation, and\nscene understanding, often reaching or surpassing human-level accuracy. This\nsuccess is due in part to the ability of DNNs to learn useful representations\nof high-dimensional inputs, a problem that humans must also solve. We examine\nthe relationship between the representations learned by these networks and\nhuman psychological representations recovered from similarity judgments. We\nfind that deep features learned in service of object classification account for\na significant amount of the variance in human similarity judgments for a set of\nanimal images. However, these features do not capture some qualitative\ndistinctions that are a key part of human representations. To remedy this, we\ndevelop a method for adapting deep features to align with human similarity\njudgments, resulting in image representations that can potentially be used to\nextend the scope of psychological experiments.","url_abs":"http://arxiv.org/abs/1608.02164v1","url_pdf":"http://arxiv.org/pdf/1608.02164v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adapting-deep-network-features-to-capture","repo_url":"https://github.com/abhijain864/Project_2020_May-July","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"adapting-deep-network-features-to-capture","repo_url":"https://github.com/abhijain864/Project_Comparing_neural-nets-with-pyschological-representations-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"adapting-deep-network-features-to-capture","repo_url":"https://github.com/abhijain864/Summer_Project_2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"adapting-deep-network-features-to-capture","repo_url":"https://github.com/kbraunlich/contort_DNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adapting-deep-network-features-to-capture","repo_url":"https://github.com/pavankumar186/Paper-Implementation-Correspondence-b-w-DeepNN-and-Human-representations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.02164","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}