{"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/long-tail-learning-via-logit-adjustment","title":"Long-tail learning via logit adjustment","arxiv_id":"2007.07314","date":"2020-07-14","proceeding":"ICLR 2021 1","authors":["Aditya Krishna Menon","Sadeep Jayasumana","Ankit Singh Rawat","Himanshu Jain","Andreas Veit","Sanjiv Kumar"],"abstract":"Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples. This poses a challenge for generalisation on such labels, and also makes na\\\"ive learning biased towards dominant labels. In this paper, we present two simple modifications of standard softmax cross-entropy training to cope with these challenges. Our techniques revisit the classic idea of logit adjustment based on the label frequencies, either applied post-hoc to a trained model, or enforced in the loss during training. Such adjustment encourages a large relative margin between logits of rare versus dominant labels. These techniques unify and generalise several recent proposals in the literature, while possessing firmer statistical grounding and empirical performance.","url_abs":"https://arxiv.org/abs/2007.07314v2","url_pdf":"https://arxiv.org/pdf/2007.07314v2.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":"long-tail-learning-via-logit-adjustment","repo_url":"https://github.com/google-research/google-research/tree/master/logit_adjustment","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"long-tail-learning-via-logit-adjustment","repo_url":"https://github.com/Chumsy0725/logit-adj-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"long-tail-learning-via-logit-adjustment","repo_url":"https://github.com/hbzju/solar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"Logit adjustment","rank_in_archive_order":54,"of":69,"metrics":{"Top-1 Accuracy":"51.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.07314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.07314"}},"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/Chumsy0725/logit-adj-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hbzju/solar","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/google-research/tree/master/logit_adjustment","reach":null}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":6,"ran":1,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"c6d31cca23ad3dcd","entry":"build_loss_fn","repo":"google-research/google-research","repo_kind":"official","path":"logit_adjustment/utils.py","file_url":"https://github.com/google-research/google-research/blob/HEAD/logit_adjustment/utils.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6d31cca23ad3dcd"}},{"code_sha256_prefix":"1c4c943182783021","entry":"partial_loss","repo":"hbzju/solar","repo_kind":"listed","path":"utils/utils_loss.py","file_url":"https://github.com/hbzju/solar/blob/HEAD/utils/utils_loss.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":"1c4c943182783021"}},{"code_sha256_prefix":"b63857e236e3aafd","entry":"accuracy","repo":"Chumsy0725/logit-adj-pytorch","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Chumsy0725/logit-adj-pytorch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b63857e236e3aafd"}},{"code_sha256_prefix":"d97199a0f9061356","entry":"batch_norm2d","repo":"Chumsy0725/logit-adj-pytorch","repo_kind":"listed","path":"model.py","file_url":"https://github.com/Chumsy0725/logit-adj-pytorch/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d97199a0f9061356"}},{"code_sha256_prefix":"262f3b927be3a2b8","entry":"class_accuracy","repo":"Chumsy0725/logit-adj-pytorch","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Chumsy0725/logit-adj-pytorch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"262f3b927be3a2b8"}},{"code_sha256_prefix":"befb5e56829495b9","entry":"log_hyperparameter","repo":"Chumsy0725/logit-adj-pytorch","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Chumsy0725/logit-adj-pytorch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"befb5e56829495b9"}},{"code_sha256_prefix":"5c366b81e063413b","entry":"resnet32","repo":"Chumsy0725/logit-adj-pytorch","repo_kind":"listed","path":"model.py","file_url":"https://github.com/Chumsy0725/logit-adj-pytorch/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c366b81e063413b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}