{"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/adaptive-early-learning-correction-for","title":"Adaptive Early-Learning Correction for Segmentation from Noisy Annotations","arxiv_id":"2110.03740","date":"2021-10-07","proceeding":"CVPR 2022 1","authors":["Sheng Liu","Kangning Liu","Weicheng Zhu","Yiqiu Shen","Carlos Fernandez-Granda"],"abstract":"Deep learning in the presence of noisy annotations has been studied extensively in classification, but much less in segmentation tasks. In this work, we study the learning dynamics of deep segmentation networks trained on inaccurately-annotated data. We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an \"early-learning\" phase, before eventually memorizing the false annotations. However, in contrast to classification, memorization in segmentation does not arise simultaneously for all semantic categories. Inspired by these findings, we propose a new method for segmentation from noisy annotations with two key elements. First, we detect the beginning of the memorization phase separately for each category during training. This allows us to adaptively correct the noisy annotations in order to exploit early learning. Second, we incorporate a regularization term that enforces consistency across scales to boost robustness against annotation noise. Our method outperforms standard approaches on a medical-imaging segmentation task where noises are synthesized to mimic human annotation errors. It also provides robustness to realistic noisy annotations present in weakly-supervised semantic segmentation, achieving state-of-the-art results on PASCAL VOC 2012. Code is available at https://github.com/Kangningthu/ADELE","url_abs":"https://arxiv.org/abs/2110.03740v2","url_pdf":"https://arxiv.org/pdf/2110.03740v2.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":"adaptive-early-learning-correction-for","repo_url":"https://github.com/kangningthu/adele","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adaptive-early-learning-correction-for","repo_url":"https://github.com/shengliu66/ELR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation-1","task_name":"Weakly supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-segmentation","task_name":"Weakly supervised segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"}],"methods":[{"method_slug":"adele","method_name":"ADELE"},{"method_slug":"elr","method_name":"ELR"}],"datasets_introduced":[],"methods_introduced":[{"slug":"adele","name":"ADELE","full_name":"Adaptive Early-Learning Correction"}],"results":[{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"ADELE (DeepLabV1-ResNet38)","rank_in_archive_order":23,"of":60,"metrics":{"Mean IoU":"72.0"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"ADELE (DeepLabV1-ResNet38)","rank_in_archive_order":25,"of":73,"metrics":{"Mean IoU":"71.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.03740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03740"}},"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/kangningthu/adele","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shengliu66/ELR","reach":null}],"summary":{"ran_honours":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"2e932a495b2ab693","entry":"accuracy","repo":"kangningthu/adele","repo_kind":"official","path":"lib/datasets/metric.py","file_url":"https://github.com/kangningthu/adele/blob/HEAD/lib/datasets/metric.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e932a495b2ab693"}},{"code_sha256_prefix":"ab1c43d5635c2cf0","entry":"cross_entropy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ab1c43d5635c2cf0"}},{"code_sha256_prefix":"84f0eba9ce9b82f0","entry":"colorEncode","repo":"kangningthu/adele","repo_kind":"official","path":"lib/datasets/metric.py","file_url":"https://github.com/kangningthu/adele/blob/HEAD/lib/datasets/metric.py","link_basis":"harvester_set","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":"84f0eba9ce9b82f0"}},{"code_sha256_prefix":"5feabe579b35978a","entry":"unique","repo":"kangningthu/adele","repo_kind":"official","path":"lib/datasets/metric.py","file_url":"https://github.com/kangningthu/adele/blob/HEAD/lib/datasets/metric.py","link_basis":"harvester_set","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":"5feabe579b35978a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}