{"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-recognition-by-routing-diverse-1","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","arxiv_id":"2010.01809","date":"2020-10-05","proceeding":"ICLR 2021 1","authors":["Xudong Wang","Long Lian","Zhongqi Miao","Ziwei Liu","Stella X. Yu"],"abstract":"Natural data are often long-tail distributed over semantic classes. Existing recognition methods tackle this imbalanced classification by placing more emphasis on the tail data, through class re-balancing/re-weighting or ensembling over different data groups, resulting in increased tail accuracies but reduced head accuracies. We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and larger confusion with hard negatives for the tail. We propose a new long-tailed classifier called RoutIng Diverse Experts (RIDE). It reduces the model variance with multiple experts, reduces the model bias with a distribution-aware diversity loss, reduces the computational cost with a dynamic expert routing module. RIDE outperforms the state-of-the-art by 5% to 7% on CIFAR100-LT, ImageNet-LT and iNaturalist 2018 benchmarks. It is also a universal framework that is applicable to various backbone networks, long-tailed algorithms, and training mechanisms for consistent performance gains. Our code is available at: https://github.com/frank-xwang/RIDE-LongTailRecognition.","url_abs":"https://arxiv.org/abs/2010.01809v4","url_pdf":"https://arxiv.org/pdf/2010.01809v4.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-recognition-by-routing-diverse-1","repo_url":"https://github.com/frank-xwang/RIDE-LongTailRecognition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"long-tailed-recognition-by-routing-diverse-1","repo_url":"https://github.com/beierzhu/xerm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"imbalanced-classification","task_name":"imbalanced classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"RIDE (ResNet-50)","rank_in_archive_order":35,"of":60,"metrics":{"Top-1 Accuracy":"72.2%"},"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":"RIDE+distill","rank_in_archive_order":32,"of":66,"metrics":{"Error Rate":"50.9"},"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":"RIDE","rank_in_archive_order":36,"of":66,"metrics":{"Error Rate":"52"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"RIDE (ResNeXt-50)","rank_in_archive_order":33,"of":69,"metrics":{"Top-1 Accuracy":"56.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"RIDE (ResNet-50)","rank_in_archive_order":39,"of":69,"metrics":{"Top-1 Accuracy":"54.9"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"RIDE","rank_in_archive_order":26,"of":43,"metrics":{"Top-1 Accuracy":"72.2%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.01809","atlas_url":"https://app.syntology.ai/?focus=2010.01809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01809"}},"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":"deterministic:regex_extraction","url":"https://github.com/frank-xwang/RIDE-LongTailRecognition","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/beierzhu/xerm","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"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":0,"samples":[{"code_sha256_prefix":"e8c073b77a02b4f5","entry":"RIDELoss","repo":"frank-xwang/RIDE-LongTailRecognition","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/frank-xwang/RIDE-LongTailRecognition/blob/HEAD/model/loss.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":"e8c073b77a02b4f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}