{"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/improving-calibration-for-long-tailed-1","title":"Improving Calibration for Long-Tailed Recognition","arxiv_id":"2104.00466","date":"2021-04-01","proceeding":"CVPR 2021 1","authors":["Zhisheng Zhong","Jiequan Cui","Shu Liu","Jiaya Jia"],"abstract":"Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of miscalibration. To address it, we design two methods to improve calibration and performance in such scenarios. Motivated by the fact that predicted probability distributions of classes are highly related to the numbers of class instances, we propose label-aware smoothing to deal with different degrees of over-confidence for classes and improve classifier learning. For dataset bias between these two stages due to different samplers, we further propose shifted batch normalization in the decoupling framework. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets, including CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, Places-LT, and iNaturalist 2018. Code will be available at https://github.com/Jia-Research-Lab/MiSLAS.","url_abs":"https://arxiv.org/abs/2104.00466v1","url_pdf":"https://arxiv.org/pdf/2104.00466v1.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":"improving-calibration-for-long-tailed-1","repo_url":"https://github.com/Jia-Research-Lab/MiSLAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"improving-calibration-for-long-tailed-1","repo_url":"https://github.com/dvlab-research/MiSLAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"improving-calibration-for-long-tailed-1","repo_url":"https://github.com/dvlab-research/imbalanced-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"improving-calibration-for-long-tailed-1","repo_url":"https://github.com/dvlab-research/rescom","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improving-calibration-for-long-tailed-1","repo_url":"https://github.com/simonustc/imbalance_ppl_cri","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=10)","model":"MiSLAS","rank_in_archive_order":18,"of":50,"metrics":{"Error Rate":"10"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-10-LT (ρ=100)","model":"MiSLAS","rank_in_archive_order":18,"of":28,"metrics":{"Error Rate":"17.9"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"MiSLAS","rank_in_archive_order":18,"of":31,"metrics":{"Error Rate":"36.8"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"MiSLAS","rank_in_archive_order":39,"of":66,"metrics":{"Error Rate":"53"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-50","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=50)","model":"MiSLAS","rank_in_archive_order":20,"of":25,"metrics":{"Error Rate":"47.7"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"MiSLAS","rank_in_archive_order":48,"of":69,"metrics":{"Top-1 Accuracy":"52.7"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"MiSLAS","rank_in_archive_order":29,"of":43,"metrics":{"Top-1 Accuracy":"71.6%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.00466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00466"}},"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/dvlab-research/imbalanced-learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Jia-Research-Lab/MiSLAS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dvlab-research/MiSLAS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dvlab-research/rescom","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simonustc/imbalance_ppl_cri","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"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":"d9def42110729a85","entry":"conv1x1","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/models/resnet.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":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/models/resnet.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":"160bb14bd76201b4"}},{"code_sha256_prefix":"97f484048ac03556","entry":"mixup_criterion","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"methods.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/methods.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97f484048ac03556"}},{"code_sha256_prefix":"345e624f9cc2e32a","entry":"mixup_data","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"methods.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/methods.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"345e624f9cc2e32a"}},{"code_sha256_prefix":"830214b89e793de5","entry":"compute_calibration","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"reliability_diagrams.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/reliability_diagrams.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":"830214b89e793de5"}},{"code_sha256_prefix":"722e0bb5cb9f0a0d","entry":"reliability_diagram","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"reliability_diagrams.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/reliability_diagrams.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":"722e0bb5cb9f0a0d"}},{"code_sha256_prefix":"8e0350d0dc4d57da","entry":"reliability_diagrams","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"reliability_diagrams.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/reliability_diagrams.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":"8e0350d0dc4d57da"}},{"code_sha256_prefix":"bc07600de5b8bbda","entry":"resnet10","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/models/resnet.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":"bc07600de5b8bbda"}},{"code_sha256_prefix":"11d038f53d77a8d2","entry":"resnet32","repo":"Jia-Research-Lab/MiSLAS","repo_kind":"official","path":"models/resnet_cifar.py","file_url":"https://github.com/Jia-Research-Lab/MiSLAS/blob/HEAD/models/resnet_cifar.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":"11d038f53d77a8d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}