{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/label-retrieval-augmented-diffusion-models-1","title":"Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels","arxiv_id":"2305.19518","date":"2023-05-31","proceeding":"NeurIPS 2023 11","authors":["Jian Chen","Ruiyi Zhang","Tong Yu","Rohan Sharma","Zhiqiang Xu","Tong Sun","Changyou Chen"],"abstract":"Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods typically rely on strict assumptions and are limited to certain types of label noise. In this paper, we reformulate the label-noise problem from a generative-model perspective, $\\textit{i.e.}$, labels are generated by gradually refining an initial random guess. This new perspective immediately enables existing powerful diffusion models to seamlessly learn the stochastic generative process. Once the generative uncertainty is modeled, we can perform classification inference using maximum likelihood estimation of labels. To mitigate the impact of noisy labels, we propose the $\\textbf{L}$abel-$\\textbf{R}$etrieval-$\\textbf{A}$ugmented (LRA) diffusion model, which leverages neighbor consistency to effectively construct pseudo-clean labels for diffusion training. Our model is flexible and general, allowing easy incorporation of different types of conditional information, $\\textit{e.g.}$, use of pre-trained models, to further boost model performance. Extensive experiments are conducted for evaluation. Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets. Remarkably, by incorporating conditional information from the powerful CLIP model, our method can boost the current SOTA accuracy by 10-20 absolute points in many cases.","url_abs":"https://arxiv.org/abs/2305.19518v2","url_pdf":"https://arxiv.org/pdf/2305.19518v2.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":"label-retrieval-augmented-diffusion-models-1","repo_url":"https://github.com/puar-playground/lra-diffusion","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":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-clothing1m","task":"Image Classification","dataset":"Clothing1M","model":"LRA-diffusion (CC)","rank_in_archive_order":1,"of":51,"metrics":{"Accuracy":"75.7%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-food-101n-1","task":"Image Classification","dataset":"Food-101N","model":"LRA-diffusion (CLIP ViT)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"93.42"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"LRA-diffusion (CLIP ViT)","rank_in_archive_order":1,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"82.56","Top-1 Accuracy":"84.16"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.19518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19518"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/puar-playground/lra-diffusion","reach":null}],"summary":{"ran":4,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a89b8862957e5753","entry":"Bottleneck","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"model_diffusion.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/model_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a89b8862957e5753"}},{"code_sha256_prefix":"44772e75d843b9de","entry":"ConditionalLinear","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"model_diffusion.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/model_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44772e75d843b9de"}},{"code_sha256_prefix":"587c31bba00d49a3","entry":"ConditionalModel","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"model_diffusion.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/model_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"587c31bba00d49a3"}},{"code_sha256_prefix":"75eae7792fcbf493","entry":"ResNet","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"model_diffusion.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/model_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75eae7792fcbf493"}},{"code_sha256_prefix":"f46dae1e37fe3580","entry":"resnet18","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"model_diffusion.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/model_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f46dae1e37fe3580"}},{"code_sha256_prefix":"501f4b5cb5ea803a","entry":"resnet34","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"model_diffusion.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/model_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"501f4b5cb5ea803a"}},{"code_sha256_prefix":"6f8aedc90a1411e5","entry":"resnet50","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"model_diffusion.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/model_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f8aedc90a1411e5"}},{"code_sha256_prefix":"2d12f1aeca8d130b","entry":"Diffusion","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"model_diffusion.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/model_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d12f1aeca8d130b"}},{"code_sha256_prefix":"1c95f06ac63ad9f3","entry":"test","repo":"puar-playground/lra-diffusion","repo_kind":"official","path":"train_CIFAR.py","file_url":"https://github.com/puar-playground/lra-diffusion/blob/HEAD/train_CIFAR.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c95f06ac63ad9f3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}