{"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/balanced-meta-softmax-for-long-tailed-visual","title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","arxiv_id":"2007.10740","date":"2020-07-21","proceeding":"NeurIPS 2020 12","authors":["Jiawei Ren","Cunjun Yu","Shunan Sheng","Xiao Ma","Haiyu Zhao","Shuai Yi","Hongsheng Li"],"abstract":"Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distributions. In this paper, we show that the Softmax function, though used in most classification tasks, gives a biased gradient estimation under the long-tailed setup. This paper presents Balanced Softmax, an elegant unbiased extension of Softmax, to accommodate the label distribution shift between training and testing. Theoretically, we derive the generalization bound for multiclass Softmax regression and show our loss minimizes the bound. In addition, we introduce Balanced Meta-Softmax, applying a complementary Meta Sampler to estimate the optimal class sample rate and further improve long-tailed learning. In our experiments, we demonstrate that Balanced Meta-Softmax outperforms state-of-the-art long-tailed classification solutions on both visual recognition and instance segmentation tasks.","url_abs":"https://arxiv.org/abs/2007.10740v3","url_pdf":"https://arxiv.org/pdf/2007.10740v3.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":"balanced-meta-softmax-for-long-tailed-visual","repo_url":"https://github.com/jiawei-ren/BalancedMetaSoftmax","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"Balanced Softmax (BALMS)","rank_in_archive_order":7,"of":50,"metrics":{"Error Rate":"8.7"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"BALMS","rank_in_archive_order":61,"of":69,"metrics":{"Top-1 Accuracy":"41.8"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"BALMS","rank_in_archive_order":23,"of":29,"metrics":{"Top-1 Accuracy":"38.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.10740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10740"}},"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":"deterministic:regex_extraction","url":"https://github.com/jiawei-ren/BalancedMetaSoftmax","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"community":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"d3cf8659227d9fa6","entry":"balanced_softmax_loss","repo":"jiawei-ren/BalancedMetaSoftmax-Classification","repo_kind":"community","path":"loss/BalancedSoftmaxLoss.py","file_url":"https://github.com/jiawei-ren/BalancedMetaSoftmax-Classification/blob/HEAD/loss/BalancedSoftmaxLoss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d3cf8659227d9fa6"}},{"code_sha256_prefix":"b30a377cff8dd790","entry":"create_loss","repo":"jiawei-ren/BalancedMetaSoftmax-Classification","repo_kind":"community","path":"loss/BalancedSoftmaxLoss.py","file_url":"https://github.com/jiawei-ren/BalancedMetaSoftmax-Classification/blob/HEAD/loss/BalancedSoftmaxLoss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b30a377cff8dd790"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}