{"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/maintaining-discrimination-and-fairness-in","title":"Maintaining Discrimination and Fairness in Class Incremental Learning","arxiv_id":"1911.07053","date":"2019-11-16","proceeding":"CVPR 2020 6","authors":["Bowen Zhao","Xi Xiao","Guojun Gan","Bin Zhang","Shu-Tao Xia"],"abstract":"Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic forgetting. Knowledge distillation (KD) is a commonly used technique to alleviate this problem. In this paper, we demonstrate it can indeed help the model to output more discriminative results within old classes. However, it cannot alleviate the problem that the model tends to classify objects into new classes, causing the positive effect of KD to be hidden and limited. We observed that an important factor causing catastrophic forgetting is that the weights in the last fully connected (FC) layer are highly biased in class incremental learning. In this paper, we propose a simple and effective solution motivated by the aforementioned observations to address catastrophic forgetting. Firstly, we utilize KD to maintain the discrimination within old classes. Then, to further maintain the fairness between old classes and new classes, we propose Weight Aligning (WA) that corrects the biased weights in the FC layer after normal training process. Unlike previous work, WA does not require any extra parameters or a validation set in advance, as it utilizes the information provided by the biased weights themselves. The proposed method is evaluated on ImageNet-1000, ImageNet-100, and CIFAR-100 under various settings. Experimental results show that the proposed method can effectively alleviate catastrophic forgetting and significantly outperform state-of-the-art methods.","url_abs":"https://arxiv.org/abs/1911.07053v1","url_pdf":"https://arxiv.org/pdf/1911.07053v1.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":"maintaining-discrimination-and-fairness-in","repo_url":"https://github.com/g-u-n/pycil","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"maintaining-discrimination-and-fairness-in","repo_url":"https://github.com/wannaa/c-flat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/incremental-learning-on-cifar-100-b0-5steps","task":"Incremental Learning","dataset":"CIFAR-100-B0(5steps of 20 classes)","model":"WA","rank_in_archive_order":6,"of":10,"metrics":{"Average Incremental Accuracy":"72.81"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet-10-steps","task":"Incremental Learning","dataset":"ImageNet - 10 steps","model":"WA","rank_in_archive_order":7,"of":10,"metrics":{"# M Params":"11.68","Average Incremental Accuracy":"65.67","Average Incremental Accuracy Top-5":"86.60","Final Accuracy":"55.60","Final Accuracy Top-5":"81.10"},"uses_additional_data":false},{"leaderboard":"/sota/incremental-learning-on-imagenet100-10-steps","task":"Incremental Learning","dataset":"ImageNet100 - 10 steps","model":"WA","rank_in_archive_order":9,"of":13,"metrics":{"# M Params":"11.22","Average Incremental Accuracy Top-5":"91.00","Final Accuracy Top-5":"84.10"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.07053","atlas_url":"https://app.syntology.ai/?focus=1911.07053","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":"1911.07053"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1911.07053\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1911.07053"},"call":"get_concepts_for_paper(arxiv_id=\"1911.07053\")"}],"by_repo":[{"repo":"g-u-n/pycil","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.05792"],"harvested_for_calls":[{"arxiv_id":"2301.05792","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.05792"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.05792\")"}]},{"repo":"wannaa/c-flat","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2404.00986"],"harvested_for_calls":[{"arxiv_id":"2404.00986","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.00986"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.00986\")"}]}],"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":"f2b454afc19d1dba78be85a71a63d9d27e1f149b0d29a00dae7a5ba6cb972c02","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}