{"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/posterior-re-calibration-for-imbalanced","title":"Posterior Re-calibration for Imbalanced Datasets","arxiv_id":"2010.11820","date":"2020-10-22","proceeding":"NeurIPS 2020 12","authors":["Junjiao Tian","Yen-Cheng Liu","Nathan Glaser","Yen-Chang Hsu","Zsolt Kira"],"abstract":"Neural Networks can perform poorly when the training label distribution is heavily imbalanced, as well as when the testing data differs from the training distribution. In order to deal with shift in the testing label distribution, which imbalance causes, we motivate the problem from the perspective of an optimal Bayes classifier and derive a post-training prior rebalancing technique that can be solved through a KL-divergence based optimization. This method allows a flexible post-training hyper-parameter to be efficiently tuned on a validation set and effectively modify the classifier margin to deal with this imbalance. We further combine this method with existing likelihood shift methods, re-interpreting them from the same Bayesian perspective, and demonstrating that our method can deal with both problems in a unified way. The resulting algorithm can be conveniently used on probabilistic classification problems agnostic to underlying architectures. Our results on six different datasets and five different architectures show state of art accuracy, including on large-scale imbalanced datasets such as iNaturalist for classification and Synthia for semantic segmentation. Please see https://github.com/GT-RIPL/UNO-IC.git for implementation.","url_abs":"https://arxiv.org/abs/2010.11820v1","url_pdf":"https://arxiv.org/pdf/2010.11820v1.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":[],"tasks":[{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"CE-DRW-IC","rank_in_archive_order":31,"of":31,"metrics":{"Error Rate":"41.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"CE-DRW-IC","rank_in_archive_order":58,"of":66,"metrics":{"Error Rate":"56.9"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"CE-DRW-IC","rank_in_archive_order":41,"of":43,"metrics":{"Top-1 Accuracy":"67.9%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.11820","atlas_url":"https://app.syntology.ai/?focus=2010.11820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11820"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/GT-RIPL/UNO-IC","reach":null}],"summary":{"ran_violates":1},"by_repo_kind":{"found_in_text":{"samples":1,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"6e80a81240f60ed0","entry":"prior_recbalancing","repo":"GT-RIPL/UNO-IC","repo_kind":"found_in_text","path":"classification/rebalancing.py","file_url":"https://github.com/GT-RIPL/UNO-IC/blob/HEAD/classification/rebalancing.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e80a81240f60ed0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}