{"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/rsg-a-simple-but-effective-module-for","title":"RSG: A Simple but Effective Module for Learning Imbalanced Datasets","arxiv_id":"2106.09859","date":"2021-06-18","proceeding":"CVPR 2021 1","authors":["JianFeng Wang","Thomas Lukasiewicz","Xiaolin Hu","Jianfei Cai","Zhenghua Xu"],"abstract":"Imbalanced datasets widely exist in practice and area great challenge for training deep neural models with agood generalization on infrequent classes. In this work, wepropose a new rare-class sample generator (RSG) to solvethis problem. RSG aims to generate some new samplesfor rare classes during training, and it has in particularthe following advantages: (1) it is convenient to use andhighly versatile, because it can be easily integrated intoany kind of convolutional neural network, and it works wellwhen combined with different loss functions, and (2) it isonly used during the training phase, and therefore, no ad-ditional burden is imposed on deep neural networks duringthe testing phase. In extensive experimental evaluations, weverify the effectiveness of RSG. Furthermore, by leveragingRSG, we obtain competitive results on Imbalanced CIFARand new state-of-the-art results on Places-LT, ImageNet-LT, and iNaturalist 2018. The source code is available at https://github.com/Jianf-Wang/RSG.","url_abs":"https://arxiv.org/abs/2106.09859v1","url_pdf":"https://arxiv.org/pdf/2106.09859v1.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":"rsg-a-simple-but-effective-module-for","repo_url":"https://github.com/Jianf-Wang/RSG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"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-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"LDAM-DRW-RSG","rank_in_archive_order":52,"of":66,"metrics":{"Error Rate":"55.5"},"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":"LDAM-DRW-RSG","rank_in_archive_order":24,"of":25,"metrics":{"Error Rate":"51.5"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"LDAM-DRS-RSG","rank_in_archive_order":50,"of":69,"metrics":{"Top-1 Accuracy":"51.8"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"LDAM-DRS-RSG","rank_in_archive_order":19,"of":29,"metrics":{"Top-1 Accuracy":"39.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"LDAM-DRS-RSG","rank_in_archive_order":31,"of":43,"metrics":{"Top-1 Accuracy":"70.3%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.09859","atlas_url":"https://app.syntology.ai/?focus=2106.09859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09859"}},"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/Jianf-Wang/RSG","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":"54209fecacac35e9","entry":"RSG","repo":"Jianf-Wang/RSG","repo_kind":"official","path":"Imbalanced_Classification/models/RSG.py","file_url":"https://github.com/Jianf-Wang/RSG/blob/HEAD/Imbalanced_Classification/models/RSG.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":"54209fecacac35e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}