{"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/long-tailed-visual-recognition-via-gaussian-1","title":"Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment","arxiv_id":"2305.11733","date":"2023-05-19","proceeding":"CVPR 2022 1","authors":["Mengke Li","Yiu-ming Cheung","Yang Lu"],"abstract":"Long-tailed data is still a big challenge for deep neural networks, even though they have achieved great success on balanced data. We observe that vanilla training on long-tailed data with cross-entropy loss makes the instance-rich head classes severely squeeze the spatial distribution of the tail classes, which leads to difficulty in classifying tail class samples. Furthermore, the original cross-entropy loss can only propagate gradient short-lively because the gradient in softmax form rapidly approaches zero as the logit difference increases. This phenomenon is called softmax saturation. It is unfavorable for training on balanced data, but can be utilized to adjust the validity of the samples in long-tailed data, thereby solving the distorted embedding space of long-tailed problems. To this end, this paper proposes the Gaussian clouded logit adjustment by Gaussian perturbation of different class logits with varied amplitude. We define the amplitude of perturbation as cloud size and set relatively large cloud sizes to tail classes. The large cloud size can reduce the softmax saturation and thereby making tail class samples more active as well as enlarging the embedding space. To alleviate the bias in a classifier, we therefore propose the class-based effective number sampling strategy with classifier re-training. Extensive experiments on benchmark datasets validate the superior performance of the proposed method. Source code is available at https://github.com/Keke921/GCLLoss.","url_abs":"https://arxiv.org/abs/2305.11733v1","url_pdf":"https://arxiv.org/pdf/2305.11733v1.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":"long-tailed-visual-recognition-via-gaussian-1","repo_url":"https://github.com/keke921/gclloss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"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":"GCLLoss","rank_in_archive_order":30,"of":50,"metrics":{"Error Rate":"10.77"},"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":"GCL","rank_in_archive_order":15,"of":28,"metrics":{"Error Rate":"17.32"},"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":"GCL","rank_in_archive_order":33,"of":66,"metrics":{"Error Rate":"51.29"},"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":"GCL","rank_in_archive_order":19,"of":25,"metrics":{"Error Rate":"46.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.11733","atlas_url":"https://app.syntology.ai/?focus=2305.11733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11733"}},"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/keke921/gclloss","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":2,"samples":[{"code_sha256_prefix":"1b3f82e6c53766e7","entry":"focal_loss","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1b3f82e6c53766e7"}},{"code_sha256_prefix":"5c74271a972c2eb0","entry":"validate","repo":"keke921/gclloss","repo_kind":"official","path":"cifar_train_backbone.py","file_url":"https://github.com/keke921/gclloss/blob/HEAD/cifar_train_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5c74271a972c2eb0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}