{"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/disentangling-label-distribution-for-long","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","arxiv_id":"2012.00321","date":"2020-12-01","proceeding":"CVPR 2021 1","authors":["Youngkyu Hong","Seungju Han","Kwanghee Choi","Seokjun Seo","Beomsu Kim","Buru Chang"],"abstract":"The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has questionable practicality since the target may also be long-tailed. Therefore, we formulate long-tailed visual recognition as a label shift problem where the target and source label distributions are different. One of the significant hurdles in dealing with the label shift problem is the entanglement between the source label distribution and the model prediction. In this paper, we focus on disentangling the source label distribution from the model prediction. We first introduce a simple but overlooked baseline method that matches the target label distribution by post-processing the model prediction trained by the cross-entropy loss and the Softmax function. Although this method surpasses state-of-the-art methods on benchmark datasets, it can be further improved by directly disentangling the source label distribution from the model prediction in the training phase. Thus, we propose a novel method, LAbel distribution DisEntangling (LADE) loss based on the optimal bound of Donsker-Varadhan representation. LADE achieves state-of-the-art performance on benchmark datasets such as CIFAR-100-LT, Places-LT, ImageNet-LT, and iNaturalist 2018. Moreover, LADE outperforms existing methods on various shifted target label distributions, showing the general adaptability of our proposed method.","url_abs":"https://arxiv.org/abs/2012.00321v2","url_pdf":"https://arxiv.org/pdf/2012.00321v2.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":"disentangling-label-distribution-for-long","repo_url":"https://github.com/hyperconnect/LADE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"disentangling-label-distribution-for-long","repo_url":"https://github.com/beierzhu/xerm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"LADE","rank_in_archive_order":38,"of":60,"metrics":{"Top-1 Accuracy":"70.0%"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"LADE","rank_in_archive_order":31,"of":50,"metrics":{"Error Rate":"11.22"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"LADE","rank_in_archive_order":21,"of":31,"metrics":{"Error Rate":"38.3"},"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":"LADE","rank_in_archive_order":48,"of":66,"metrics":{"Error Rate":"54.6"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"LADE","rank_in_archive_order":46,"of":69,"metrics":{"Top-1 Accuracy":"53.0"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"LADE","rank_in_archive_order":22,"of":29,"metrics":{"Top-1 Accuracy":"38.8"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"LADE","rank_in_archive_order":35,"of":43,"metrics":{"Top-1 Accuracy":"70.0%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.00321","atlas_url":"https://app.syntology.ai/?focus=2012.00321","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":"2012.00321"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.00321\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.00321"},"call":"get_concepts_for_paper(arxiv_id=\"2012.00321\")"}],"by_repo":[{"repo":"hyperconnect/LADE","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"beierzhu/xerm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2009.12991"],"harvested_for_calls":[{"arxiv_id":"2009.12991","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2009.12991"},"call":"get_harvested_code_for_paper(arxiv_id=\"2009.12991\")"}]}],"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":"d0a16501bcdcf4e10bd431f1139bf96edd5886958eba174967e6b89e2d1f11be","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}