{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/on-the-capability-of-neural-networks-to","title":"When and how CNNs generalize to out-of-distribution category-viewpoint combinations","arxiv_id":"2007.08032","date":"2020-07-15","proceeding":null,"authors":["Spandan Madan","Timothy Henry","Jamell Dozier","Helen Ho","Nishchal Bhandari","Tomotake Sasaki","Frédo Durand","Hanspeter Pfister","Xavier Boix"],"abstract":"Object recognition and viewpoint estimation lie at the heart of visual understanding. Recent works suggest that convolutional neural networks (CNNs) fail to generalize to out-of-distribution (OOD) category-viewpoint combinations, ie. combinations not seen during training. In this paper, we investigate when and how such OOD generalization may be possible by evaluating CNNs trained to classify both object category and 3D viewpoint on OOD combinations, and identifying the neural mechanisms that facilitate such OOD generalization. We show that increasing the number of in-distribution combinations (ie. data diversity) substantially improves generalization to OOD combinations, even with the same amount of training data. We compare learning category and viewpoint in separate and shared network architectures, and observe starkly different trends on in-distribution and OOD combinations, ie. while shared networks are helpful in-distribution, separate networks significantly outperform shared ones at OOD combinations. Finally, we demonstrate that such OOD generalization is facilitated by the neural mechanism of specialization, ie. the emergence of two types of neurons -- neurons selective to category and invariant to viewpoint, and vice versa.","url_abs":"https://arxiv.org/abs/2007.08032v3","url_pdf":"https://arxiv.org/pdf/2007.08032v3.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":"on-the-capability-of-neural-networks-to","repo_url":"https://github.com/Spandan-Madan/generalization_biased_category_pose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-the-capability-of-neural-networks-to","repo_url":"https://github.com/spandan-madan/in_distribution_adversarial_examples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"viewpoint-estimation","task_name":"Viewpoint Estimation"}],"methods":[],"datasets_introduced":[{"slug":"biased-cars","name":"Biased-Cars","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.08032","atlas_url":"https://app.syntology.ai/?focus=2007.08032","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2007.08032"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2007.08032\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2007.08032"},"call":"get_concepts_for_paper(arxiv_id=\"2007.08032\")"}],"by_repo":[{"repo":"Spandan-Madan/generalization_biased_category_pose","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"spandan-madan/in_distribution_adversarial_examples","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.16198"],"harvested_for_calls":[{"arxiv_id":"2106.16198","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.16198"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.16198\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"89d07287cb0d564d4a8947e559db0c5cba487a2b399b75e8f6436e0cd989d04d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}