{"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-gans-for-long-tailed-data-through","title":"Improving GANs for Long-Tailed Data through Group Spectral Regularization","arxiv_id":"2208.09932","date":"2022-08-21","proceeding":null,"authors":["Harsh Rangwani","Naman Jaswani","Tejan Karmali","Varun Jampani","R. Venkatesh Babu"],"abstract":"Deep long-tailed learning aims to train useful deep networks on practical, real-world imbalanced distributions, wherein most labels of the tail classes are associated with a few samples. There has been a large body of work to train discriminative models for visual recognition on long-tailed distribution. In contrast, we aim to train conditional Generative Adversarial Networks, a class of image generation models on long-tailed distributions. We find that similar to recognition, state-of-the-art methods for image generation also suffer from performance degradation on tail classes. The performance degradation is mainly due to class-specific mode collapse for tail classes, which we observe to be correlated with the spectral explosion of the conditioning parameter matrix. We propose a novel group Spectral Regularizer (gSR) that prevents the spectral explosion alleviating mode collapse, which results in diverse and plausible image generation even for tail classes. We find that gSR effectively combines with existing augmentation and regularization techniques, leading to state-of-the-art image generation performance on long-tailed data. Extensive experiments demonstrate the efficacy of our regularizer on long-tailed datasets with different degrees of imbalance.","url_abs":"https://arxiv.org/abs/2208.09932v1","url_pdf":"https://arxiv.org/pdf/2208.09932v1.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-gans-for-long-tailed-data-through","repo_url":"https://github.com/val-iisc/gSRGAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"bigan","method_name":"BiGAN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-cifar-10-lt","task":"Conditional Image Generation","dataset":"CIFAR-10 LT","model":"BigGAN + gSR","rank_in_archive_order":1,"of":1,"metrics":{"FID":"12.03"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-lsun","task":"Image Generation","dataset":"LSUN","model":"BigGAN + gSR","rank_in_archive_order":1,"of":1,"metrics":{"Average FID":"20.18"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-inaturalist-2019","task":"Image Generation","dataset":"iNaturalist 2019","model":"BigGAN + gSR","rank_in_archive_order":2,"of":2,"metrics":{"FID":"13.95"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.09932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.09932"}},"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/val-iisc/gSRGAN","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"609baa7e05b85a4d","entry":"DiscBlock","repo":"val-iisc/gSRGAN","repo_kind":"official","path":"src/models/resnet.py","file_url":"https://github.com/val-iisc/gSRGAN/blob/HEAD/src/models/resnet.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":"609baa7e05b85a4d"}},{"code_sha256_prefix":"b3486b117e763bdf","entry":"DiscOptBlock","repo":"val-iisc/gSRGAN","repo_kind":"official","path":"src/models/resnet.py","file_url":"https://github.com/val-iisc/gSRGAN/blob/HEAD/src/models/resnet.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":"b3486b117e763bdf"}},{"code_sha256_prefix":"14af0f78c3a1e2e2","entry":"Discriminator","repo":"val-iisc/gSRGAN","repo_kind":"official","path":"src/models/resnet.py","file_url":"https://github.com/val-iisc/gSRGAN/blob/HEAD/src/models/resnet.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":"14af0f78c3a1e2e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}