{"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/learning-to-transform-for-generalizable-1","title":"Learning to Transform for Generalizable Instance-wise Invariance","arxiv_id":"2309.16672","date":"2023-09-28","proceeding":"ICCV 2023 1","authors":["Utkarsh Singhal","Carlos Esteves","Ameesh Makadia","Stella X. Yu"],"abstract":"Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or hard-coding invariances into the architecture. However, too much or too little invariance can hurt, and the correct amount is unknown a priori and dependent on the instance. Ideally, the appropriate invariance would be learned from data and inferred at test-time. We treat invariance as a prediction problem. Given any image, we use a normalizing flow to predict a distribution over transformations and average the predictions over them. Since this distribution only depends on the instance, we can align instances before classifying them and generalize invariance across classes. The same distribution can also be used to adapt to out-of-distribution poses. This normalizing flow is trained end-to-end and can learn a much larger range of transformations than Augerino and InstaAug. When used as data augmentation, our method shows accuracy and robustness gains on CIFAR 10, CIFAR10-LT, and TinyImageNet.","url_abs":"https://arxiv.org/abs/2309.16672v3","url_pdf":"https://arxiv.org/pdf/2309.16672v3.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":"learning-to-transform-for-generalizable-1","repo_url":"https://github.com/sutkarsh/flow_inv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.16672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16672"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sutkarsh/flow_inv","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"181c4a83675a810f","entry":"get_model_optimizer","repo":"sutkarsh/flow_inv","repo_kind":"official","path":"learned_inv/lila/flow_invariance.py","file_url":"https://github.com/sutkarsh/flow_inv/blob/HEAD/learned_inv/lila/flow_invariance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"181c4a83675a810f"}},{"code_sha256_prefix":"e8537cdf4793433f","entry":"get_scheduler","repo":"sutkarsh/flow_inv","repo_kind":"official","path":"learned_inv/lila/flow_invariance.py","file_url":"https://github.com/sutkarsh/flow_inv/blob/HEAD/learned_inv/lila/flow_invariance.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8537cdf4793433f"}},{"code_sha256_prefix":"2908722507998e9f","entry":"flow_invariance","repo":"sutkarsh/flow_inv","repo_kind":"official","path":"learned_inv/lila/flow_invariance.py","file_url":"https://github.com/sutkarsh/flow_inv/blob/HEAD/learned_inv/lila/flow_invariance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2908722507998e9f"}},{"code_sha256_prefix":"00d665462fb90958","entry":"valid_performance","repo":"sutkarsh/flow_inv","repo_kind":"official","path":"learned_inv/lila/flow_invariance.py","file_url":"https://github.com/sutkarsh/flow_inv/blob/HEAD/learned_inv/lila/flow_invariance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00d665462fb90958"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}