{"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/distribution-aware-robust-learning-from-long","title":"Distribution-Aware Robust Learning from Long-Tailed Data with Noisy Labels","arxiv_id":"2407.16802","date":"2024-07-23","proceeding":null,"authors":["Jae Soon Baik","In Young Yoon","Kun Hoon Kim","Jun Won Choi"],"abstract":"Deep neural networks have demonstrated remarkable advancements in various fields using large, well-annotated datasets. However, real-world data often exhibit long-tailed distributions and label noise, significantly degrading generalization performance. Recent studies addressing these issues have focused on noisy sample selection methods that estimate the centroid of each class based on high-confidence samples within each target class. The performance of these methods is limited because they use only the training samples within each class for class centroid estimation, making the quality of centroids susceptible to long-tailed distributions and noisy labels. In this study, we present a robust training framework called Distribution-aware Sample Selection and Contrastive Learning (DaSC). Specifically, DaSC introduces a Distribution-aware Class Centroid Estimation (DaCC) to generate enhanced class centroids. DaCC performs weighted averaging of the features from all samples, with weights determined based on model predictions. Additionally, we propose a confidence-aware contrastive learning strategy to obtain balanced and robust representations. The training samples are categorized into high-confidence and low-confidence samples. Our method then applies Semi-supervised Balanced Contrastive Loss (SBCL) using high-confidence samples, leveraging reliable label information to mitigate class bias. For the low-confidence samples, our method computes Mixup-enhanced Instance Discrimination Loss (MIDL) to improve their representations in a self-supervised manner. Our experimental results on CIFAR and real-world noisy-label datasets demonstrate the superior performance of the proposed DaSC compared to previous approaches.","url_abs":"https://arxiv.org/abs/2407.16802v1","url_pdf":"https://arxiv.org/pdf/2407.16802v1.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":"distribution-aware-robust-learning-from-long","repo_url":"https://github.com/jaesoonbaik1213/dasc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.16802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16802"}},"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":"deterministic:regex_extraction","url":"https://github.com/JaesoonBaik1213/DaSC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":13,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":17,"ran":14,"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":"edb2f37e016d955a","entry":"Preact_ResNet18","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"models/PreResNet.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/models/PreResNet.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":"edb2f37e016d955a"}},{"code_sha256_prefix":"621298c338df1815","entry":"ResNet18","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"models/PreResNet.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/models/PreResNet.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":"621298c338df1815"}},{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"models/PreResNet.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/models/PreResNet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"d6b493f24b80f8d3","entry":"get_imbalance_ratios","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"datas/dataloader_red_mini_imagenet.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/datas/dataloader_red_mini_imagenet.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":"d6b493f24b80f8d3"}},{"code_sha256_prefix":"23afa08e1cbdacce","entry":"get_imbalance_ratios_1","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"datas/data_utils_N.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/datas/data_utils_N.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":"23afa08e1cbdacce"}},{"code_sha256_prefix":"b419771b07d6b313","entry":"get_img_num_per_cls","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"datas/dataloader_red_mini_imagenet.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/datas/dataloader_red_mini_imagenet.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":"b419771b07d6b313"}},{"code_sha256_prefix":"04303b0f4abc9b27","entry":"sample_dataset","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"datas/dataloader_red_mini_imagenet.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/datas/dataloader_red_mini_imagenet.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":"04303b0f4abc9b27"}},{"code_sha256_prefix":"a399ccf88d7166c6","entry":"sample_dataset_1","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"datas/data_utils.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/datas/data_utils.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":"a399ccf88d7166c6"}},{"code_sha256_prefix":"082b83cd93beed20","entry":"sample_dataset_1","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"datas/data_utils_N.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/datas/data_utils_N.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":"082b83cd93beed20"}},{"code_sha256_prefix":"1edaa58918fd8481","entry":"set_device","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"settings/configs.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/settings/configs.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":"1edaa58918fd8481"}},{"code_sha256_prefix":"56df0904ca7bc6a3","entry":"set_tensor","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"utils/util.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/utils/util.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":"56df0904ca7bc6a3"}},{"code_sha256_prefix":"0d26b5abf61353f9","entry":"to_var","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/models/resnet.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":"0d26b5abf61353f9"}},{"code_sha256_prefix":"5543609031c0e900","entry":"unpickle","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"datas/data_utils.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/datas/data_utils.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":"5543609031c0e900"}},{"code_sha256_prefix":"ef49e82a7403eee1","entry":"unpickle","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"datas/data_utils_N.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/datas/data_utils_N.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":"ef49e82a7403eee1"}},{"code_sha256_prefix":"f0c9a29156911331","entry":"accuracy","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"models/metric.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/models/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":"f0c9a29156911331"}},{"code_sha256_prefix":"fd714bbda15c3c95","entry":"balanced_softmax_loss","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"experiment/train_cifar_ssl.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/experiment/train_cifar_ssl.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":"fd714bbda15c3c95"}},{"code_sha256_prefix":"15a4b28e19a85a2a","entry":"balanced_softmax_loss_semi","repo":"JaesoonBaik1213/DaSC","repo_kind":"official","path":"experiment/train_cifar_ssl.py","file_url":"https://github.com/JaesoonBaik1213/DaSC/blob/HEAD/experiment/train_cifar_ssl.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":"15a4b28e19a85a2a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}