{"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/instance-dependent-noisy-label-learning-via","title":"Instance-Dependent Noisy Label Learning via Graphical Modelling","arxiv_id":"2209.00906","date":"2022-09-02","proceeding":null,"authors":["Arpit Garg","Cuong Nguyen","Rafael Felix","Thanh-Toan Do","Gustavo Carneiro"],"abstract":"Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them. There are many types of label noise, such as symmetric, asymmetric and instance-dependent noise (IDN), with IDN being the only type that depends on image information. Such dependence on image information makes IDN a critical type of label noise to study, given that labelling mistakes are caused in large part by insufficient or ambiguous information about the visual classes present in images. Aiming to provide an effective technique to address IDN, we present a new graphical modelling approach called InstanceGM, that combines discriminative and generative models. The main contributions of InstanceGM are: i) the use of the continuous Bernoulli distribution to train the generative model, offering significant training advantages, and ii) the exploration of a state-of-the-art noisy-label discriminative classifier to generate clean labels from instance-dependent noisy-label samples. InstanceGM is competitive with current noisy-label learning approaches, particularly in IDN benchmarks using synthetic and real-world datasets, where our method shows better accuracy than the competitors in most experiments.","url_abs":"https://arxiv.org/abs/2209.00906v1","url_pdf":"https://arxiv.org/pdf/2209.00906v1.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":"instance-dependent-noisy-label-learning-via","repo_url":"https://github.com/arpit2412/InstanceGM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-clothing1m","task":"Image Classification","dataset":"Clothing1M","model":"InstanceGM","rank_in_archive_order":18,"of":51,"metrics":{"Accuracy":"74.40%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-20","task":"Image Classification","dataset":"Red MiniImageNet 20% label noise","model":"InstanceGM-SS","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"60.89"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-20","task":"Image Classification","dataset":"Red MiniImageNet 20% label noise","model":"InstanceGM","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"58.38"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-40","task":"Image Classification","dataset":"Red MiniImageNet 40% label noise","model":"InstanceGM-SS","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"56.37"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-40","task":"Image Classification","dataset":"Red MiniImageNet 40% label noise","model":"InstanceGM","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"52.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-60","task":"Image Classification","dataset":"Red MiniImageNet 60% label noise","model":"InstanceGM-SS","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"53.21"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-60","task":"Image Classification","dataset":"Red MiniImageNet 60% label noise","model":"InstanceGM","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"47.96"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-80","task":"Image Classification","dataset":"Red MiniImageNet 80% label noise","model":"InstanceGM-SS","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"44.03"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-80","task":"Image Classification","dataset":"Red MiniImageNet 80% label noise","model":"InstanceGM","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"39.62"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-animal","task":"Learning with noisy labels","dataset":"ANIMAL","model":"InstanceGM with ConvNeXt","rank_in_archive_order":11,"of":19,"metrics":{"Accuracy":"84.7","ImageNet Pretrained":"NO","Network":"ConvNeXt"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-animal","task":"Learning with noisy labels","dataset":"ANIMAL","model":"InstanceGM","rank_in_archive_order":12,"of":19,"metrics":{"Accuracy":"84.6","ImageNet Pretrained":"NO","Network":"Vgg19-BN"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-animal","task":"Learning with noisy labels","dataset":"ANIMAL","model":"InstanceGM with ResNet","rank_in_archive_order":15,"of":19,"metrics":{"Accuracy":"82.3","ImageNet Pretrained":"NO","Network":"ResNet"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10","task":"Learning with noisy labels","dataset":"CIFAR-10","model":"InstanceGM","rank_in_archive_order":1,"of":1,"metrics":{"Test Accuracy":"95.9"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-100","task":"Learning with noisy labels","dataset":"CIFAR-100","model":"InstanceGM","rank_in_archive_order":1,"of":1,"metrics":{"Test Accuracy":"77.19"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red","task":"Learning with noisy labels","dataset":"Red MiniImageNet 20% label noise","model":"InstanceGM-SS","rank_in_archive_order":3,"of":4,"metrics":{"Test Accuracy":"60.89"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red","task":"Learning with noisy labels","dataset":"Red MiniImageNet 20% label noise","model":"InstanceGM","rank_in_archive_order":4,"of":4,"metrics":{"Test Accuracy":"58.38"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-1","task":"Learning with noisy labels","dataset":"Red MiniImageNet 40% label noise","model":"InstanceGM-SS","rank_in_archive_order":3,"of":4,"metrics":{"Test Accuracy":"56.37"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-1","task":"Learning with noisy labels","dataset":"Red MiniImageNet 40% label noise","model":"InstanceGM","rank_in_archive_order":4,"of":4,"metrics":{"Test Accuracy":"52.24"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-2","task":"Learning with noisy labels","dataset":"Red MiniImageNet 60% label noise","model":"InstanceGM-SS","rank_in_archive_order":1,"of":3,"metrics":{"Test Accuracy":"53.21"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-2","task":"Learning with noisy labels","dataset":"Red MiniImageNet 60% label noise","model":"InstanceGM","rank_in_archive_order":3,"of":3,"metrics":{"Test Accuracy":"47.96"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-3","task":"Learning with noisy labels","dataset":"Red MiniImageNet 80% label noise","model":"InstanceGM-SS","rank_in_archive_order":2,"of":4,"metrics":{"Test Accuracy":"44.03"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-3","task":"Learning with noisy labels","dataset":"Red MiniImageNet 80% label noise","model":"InstanceGM","rank_in_archive_order":4,"of":4,"metrics":{"Test Accuracy":"39.62"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.00906","atlas_url":"https://app.syntology.ai/?focus=2209.00906","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":"2209.00906"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2209.00906\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2209.00906"},"call":"get_concepts_for_paper(arxiv_id=\"2209.00906\")"}],"by_repo":[{"repo":"arpit2412/InstanceGM","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":"b41dc2b2c32597730f17d684a1fd459d3b32713c2cf7b6491764e278ed915ce4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}