{"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/disturblabel-regularizing-cnn-on-the-loss","title":"DisturbLabel: Regularizing CNN on the Loss Layer","arxiv_id":"1605.00055","date":"2016-04-30","proceeding":"CVPR 2016 6","authors":["Lingxi Xie","Jingdong Wang","Zhen Wei","Meng Wang","Qi Tian"],"abstract":"During a long period of time we are combating over-fitting in the CNN\ntraining process with model regularization, including weight decay, model\naveraging, data augmentation, etc. In this paper, we present DisturbLabel, an\nextremely simple algorithm which randomly replaces a part of labels as\nincorrect values in each iteration. Although it seems weird to intentionally\ngenerate incorrect training labels, we show that DisturbLabel prevents the\nnetwork training from over-fitting by implicitly averaging over exponentially\nmany networks which are trained with different label sets. To the best of our\nknowledge, DisturbLabel serves as the first work which adds noises on the loss\nlayer. Meanwhile, DisturbLabel cooperates well with Dropout to provide\ncomplementary regularization functions. Experiments demonstrate competitive\nrecognition results on several popular image recognition datasets.","url_abs":"http://arxiv.org/abs/1605.00055v1","url_pdf":"http://arxiv.org/pdf/1605.00055v1.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":"disturblabel-regularizing-cnn-on-the-loss","repo_url":"https://github.com/amirhfarzaneh/DisturbLabel-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"disturblabel-regularizing-cnn-on-the-loss","repo_url":"https://github.com/kimy-de/DisturbMethods","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.00055","atlas_url":"https://app.syntology.ai/?focus=1605.00055","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":"1605.00055"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1605.00055\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1605.00055"},"call":"get_concepts_for_paper(arxiv_id=\"1605.00055\")"}],"by_repo":[{"repo":"amirhfarzaneh/DisturbLabel-PyTorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kimy-de/DisturbMethods","kind":"listed","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":"e145219f7b4052401f3689d5d974cfcd193bfb27d83f0dcd83ce3dc6a9f240bc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}