{"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/reslt-residual-learning-for-long-tailed","title":"ResLT: Residual Learning for Long-tailed Recognition","arxiv_id":"2101.10633","date":"2021-01-26","proceeding":null,"authors":["Jiequan Cui","Shu Liu","Zhuotao Tian","Zhisheng Zhong","Jiaya Jia"],"abstract":"Deep learning algorithms face great challenges with long-tailed data distribution which, however, is quite a common case in real-world scenarios. Previous methods tackle the problem from either the aspect of input space (re-sampling classes with different frequencies) or loss space (re-weighting classes with different weights), suffering from heavy over-fitting to tail classes or hard optimization during training. To alleviate these issues, we propose a more fundamental perspective for long-tailed recognition, i.e., from the aspect of parameter space, and aims to preserve specific capacity for classes with low frequencies. From this perspective, the trivial solution utilizes different branches for the head, medium, and tail classes respectively, and then sums their outputs as the final results is not feasible. Instead, we design the effective residual fusion mechanism -- with one main branch optimized to recognize images from all classes, another two residual branches are gradually fused and optimized to enhance images from medium+tail classes and tail classes respectively. Then the branches are aggregated into final results by additive shortcuts. We test our method on several benchmarks, i.e., long-tailed version of CIFAR-10, CIFAR-100, Places, ImageNet, and iNaturalist 2018. Experimental results manifest the effectiveness of our method. Our code is available at https://github.com/jiequancui/ResLT.","url_abs":"https://arxiv.org/abs/2101.10633v3","url_pdf":"https://arxiv.org/pdf/2101.10633v3.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":"reslt-residual-learning-for-long-tailed","repo_url":"https://github.com/jiequancui/ResLT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reslt-residual-learning-for-long-tailed","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":"reslt-residual-learning-for-long-tailed","repo_url":"https://github.com/dvlab-research/parametric-contrastive-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"reslt-residual-learning-for-long-tailed","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":"reslt-residual-learning-for-long-tailed","repo_url":"https://github.com/jiequancui/Parametric-Contrastive-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[],"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":"ResLT","rank_in_archive_order":22,"of":50,"metrics":{"Error Rate":"10.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"ResLT(ResNeXt-50-3 experts)","rank_in_archive_order":27,"of":69,"metrics":{"Top-1 Accuracy":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"ResLT(ResNeXt101-32x4d)","rank_in_archive_order":37,"of":69,"metrics":{"Top-1 Accuracy":"55.1"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"ResLT(ResNeXt50)","rank_in_archive_order":47,"of":69,"metrics":{"Top-1 Accuracy":"52.9"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"ResLT(3 experts)","rank_in_archive_order":25,"of":43,"metrics":{"Top-1 Accuracy":"72.9%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.10633","atlas_url":"https://app.syntology.ai/?focus=2101.10633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.10633"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jiequancui/ResLT","reach":null},{"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/dvlab-research/rescom","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dvlab-research/parametric-contrastive-learning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiequancui/Parametric-Contrastive-Learning","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":2,"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":8,"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":1,"samples":[{"code_sha256_prefix":"b793b278a771fd52","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b793b278a771fd52"}},{"code_sha256_prefix":"e3b2c8f412a7b141","entry":"crossEntropy","repo":"jiequancui/ResLT","repo_kind":"official","path":"Inat/iNaturalTrain_reslt.py","file_url":"https://github.com/jiequancui/ResLT/blob/HEAD/Inat/iNaturalTrain_reslt.py","link_basis":"first_harvest_node","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":"e3b2c8f412a7b141"}},{"code_sha256_prefix":"9dadc657844ac856","entry":"label_smoothing","repo":"jiequancui/ResLT","repo_kind":"official","path":"ImageNetLT/ImageNetTrain_reslt.py","file_url":"https://github.com/jiequancui/ResLT/blob/HEAD/ImageNetLT/ImageNetTrain_reslt.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9dadc657844ac856"}},{"code_sha256_prefix":"9b2fdcdcc7de945a","entry":"mixup_criterion","repo":"jiequancui/ResLT","repo_kind":"official","path":"CIFAR/cifarTrain_reslt_cifar10.py","file_url":"https://github.com/jiequancui/ResLT/blob/HEAD/CIFAR/cifarTrain_reslt_cifar10.py","link_basis":"first_harvest_node","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":"9b2fdcdcc7de945a"}},{"code_sha256_prefix":"760098c40816bbe8","entry":"mixup_data","repo":"jiequancui/ResLT","repo_kind":"official","path":"CIFAR/cifarTrain_reslt_cifar10.py","file_url":"https://github.com/jiequancui/ResLT/blob/HEAD/CIFAR/cifarTrain_reslt_cifar10.py","link_basis":"first_harvest_node","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":"760098c40816bbe8"}},{"code_sha256_prefix":"dfb9a2fb0f62176c","entry":"crossEntropy","repo":"jiequancui/ResLT","repo_kind":"official","path":"CIFAR/cifarTrain_reslt_cifar10.py","file_url":"https://github.com/jiequancui/ResLT/blob/HEAD/CIFAR/cifarTrain_reslt_cifar10.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":"dfb9a2fb0f62176c"}},{"code_sha256_prefix":"1a5cea782c37726a","entry":"crossEntropy","repo":"jiequancui/ResLT","repo_kind":"official","path":"ImageNetLT/ImageNetTrain_reslt.py","file_url":"https://github.com/jiequancui/ResLT/blob/HEAD/ImageNetLT/ImageNetTrain_reslt.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":"1a5cea782c37726a"}},{"code_sha256_prefix":"1402adb1ad919a47","entry":"validate","repo":"jiequancui/ResLT","repo_kind":"official","path":"ImageNetLT/ImageNetTrain_reslt.py","file_url":"https://github.com/jiequancui/ResLT/blob/HEAD/ImageNetLT/ImageNetTrain_reslt.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":"1402adb1ad919a47"}},{"code_sha256_prefix":"b9c94d8815e978c1","entry":"validate","repo":"jiequancui/ResLT","repo_kind":"official","path":"Inat/iNaturalTrain_reslt.py","file_url":"https://github.com/jiequancui/ResLT/blob/HEAD/Inat/iNaturalTrain_reslt.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":"b9c94d8815e978c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}