{"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/propmix-hard-sample-filtering-and","title":"PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels","arxiv_id":"2110.11809","date":"2021-10-22","proceeding":null,"authors":["Filipe R. Cordeiro","Vasileios Belagiannis","Ian Reid","Gustavo Carneiro"],"abstract":"The most competitive noisy label learning methods rely on an unsupervised classification of clean and noisy samples, where samples classified as noisy are re-labelled and \"MixMatched\" with the clean samples. These methods have two issues in large noise rate problems: 1) the noisy set is more likely to contain hard samples that are in-correctly re-labelled, and 2) the number of samples produced by MixMatch tends to be reduced because it is constrained by the small clean set size. In this paper, we introduce the learning algorithm PropMix to handle the issues above. PropMix filters out hard noisy samples, with the goal of increasing the likelihood of correctly re-labelling the easy noisy samples. Also, PropMix places clean and re-labelled easy noisy samples in a training set that is augmented with MixUp, removing the clean set size constraint and including a large proportion of correctly re-labelled easy noisy samples. We also include self-supervised pre-training to improve robustness to high noisy label scenarios. Our experiments show that PropMix has state-of-the-art (SOTA) results on CIFAR-10/-100(with symmetric, asymmetric and semantic label noise), Red Mini-ImageNet (from the Controlled Noisy Web Labels), Clothing1M and WebVision. In severe label noise bench-marks, our results are substantially better than other methods. The code is available athttps://github.com/filipe-research/PropMix.","url_abs":"https://arxiv.org/abs/2110.11809v1","url_pdf":"https://arxiv.org/pdf/2110.11809v1.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":"propmix-hard-sample-filtering-and","repo_url":"https://github.com/filipe-research/propmix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification-with-label-noise","task_name":"Image Classification with Label Noise"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-red-miniimagenet-20","task":"Image Classification","dataset":"Red MiniImageNet 20% label noise","model":"PropMix","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"61.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-40","task":"Image Classification","dataset":"Red MiniImageNet 40% label noise","model":"PropMix","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"56.22"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-60","task":"Image Classification","dataset":"Red MiniImageNet 60% label noise","model":"PropMix","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"52.84"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-80","task":"Image Classification","dataset":"Red MiniImageNet 80% label noise","model":"PropMix","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"43.42"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-webvision","task":"Image Classification","dataset":"WebVision","model":"PropMix (Ours)","rank_in_archive_order":1,"of":2,"metrics":{"Top 1 Accuracy":"78.84"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.11809","atlas_url":"https://app.syntology.ai/?focus=2110.11809","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":"2110.11809"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.11809\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.11809"},"call":"get_concepts_for_paper(arxiv_id=\"2110.11809\")"}],"by_repo":[{"repo":"filipe-research/propmix","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"f0e51a2e29514349fb44a713acc4f2322d1dea82b883b3795414f95a9c6a1f5a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}