{"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/feature-generation-for-long-tail","title":"Feature Generation for Long-tail Classification","arxiv_id":"2111.05956","date":"2021-11-10","proceeding":null,"authors":["Rahul Vigneswaran","Marc T. Law","Vineeth N. Balasubramanian","Makarand Tapaswi"],"abstract":"The visual world naturally exhibits an imbalance in the number of object or scene instances resulting in a \\emph{long-tailed distribution}. This imbalance poses significant challenges for classification models based on deep learning. Oversampling instances of the tail classes attempts to solve this imbalance. However, the limited visual diversity results in a network with poor representation ability. A simple counter to this is decoupling the representation and classifier networks and using oversampling only to train the classifier. In this paper, instead of repeatedly re-sampling the same image (and thereby features), we explore a direction that attempts to generate meaningful features by estimating the tail category's distribution. Inspired by ideas from recent work on few-shot learning, we create calibrated distributions to sample additional features that are subsequently used to train the classifier. Through several experiments on the CIFAR-100-LT (long-tail) dataset with varying imbalance factors and on mini-ImageNet-LT (long-tail), we show the efficacy of our approach and establish a new state-of-the-art. We also present a qualitative analysis of generated features using t-SNE visualizations and analyze the nearest neighbors used to calibrate the tail class distributions. Our code is available at https://github.com/rahulvigneswaran/TailCalibX.","url_abs":"https://arxiv.org/abs/2111.05956v1","url_pdf":"https://arxiv.org/pdf/2111.05956v1.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":"feature-generation-for-long-tail","repo_url":"https://github.com/rahulvigneswaran/tailcalibx","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"imbalanced-classification","task_name":"imbalanced classification"}],"methods":[],"datasets_introduced":[{"slug":"mini-imagenet-lt","name":"mini-ImageNet-LT","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"CBD+TailCalibX","rank_in_archive_order":25,"of":31,"metrics":{"Error Rate":"38.87"},"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":"CBD+TailCalibX","rank_in_archive_order":42,"of":66,"metrics":{"Error Rate":"53.41"},"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":"CBD+TailCalibX","rank_in_archive_order":22,"of":25,"metrics":{"Error Rate":"49.1"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-mini-imagenet-lt","task":"Long-tail Learning","dataset":"mini-ImageNet-LT","model":"TailCalibX","rank_in_archive_order":1,"of":1,"metrics":{"Error Rate":"55.27"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.05956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.05956"}},"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/rahulvigneswaran/tailcalibx","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"rahulvigneswaran/tailcalibx","repo_kind":"official","path":"libs/models/ResNextFeature.py","file_url":"https://github.com/rahulvigneswaran/tailcalibx/blob/HEAD/libs/models/ResNextFeature.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"9402b63618d1a522","entry":"create_model","repo":"rahulvigneswaran/tailcalibx","repo_kind":"official","path":"libs/models/CosineDotProductClassifier.py","file_url":"https://github.com/rahulvigneswaran/tailcalibx/blob/HEAD/libs/models/CosineDotProductClassifier.py","link_basis":"harvester_set","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":"9402b63618d1a522"}},{"code_sha256_prefix":"4693423b6a44b0d8","entry":"create_model","repo":"rahulvigneswaran/tailcalibx","repo_kind":"official","path":"libs/models/DotProductClassifier.py","file_url":"https://github.com/rahulvigneswaran/tailcalibx/blob/HEAD/libs/models/DotProductClassifier.py","link_basis":"harvester_set","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":"4693423b6a44b0d8"}},{"code_sha256_prefix":"1f7771ddc9823b0a","entry":"create_model","repo":"rahulvigneswaran/tailcalibx","repo_kind":"official","path":"libs/models/ResNet32Feature.py","file_url":"https://github.com/rahulvigneswaran/tailcalibx/blob/HEAD/libs/models/ResNet32Feature.py","link_basis":"harvester_set","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":"1f7771ddc9823b0a"}},{"code_sha256_prefix":"aa721c36d2d710f8","entry":"create_model","repo":"rahulvigneswaran/tailcalibx","repo_kind":"official","path":"libs/models/ResNext50Feature.py","file_url":"https://github.com/rahulvigneswaran/tailcalibx/blob/HEAD/libs/models/ResNext50Feature.py","link_basis":"harvester_set","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":"aa721c36d2d710f8"}},{"code_sha256_prefix":"1ba831f456a905ab","entry":"load_model","repo":"rahulvigneswaran/tailcalibx","repo_kind":"official","path":"libs/models/ResNext50Feature.py","file_url":"https://github.com/rahulvigneswaran/tailcalibx/blob/HEAD/libs/models/ResNext50Feature.py","link_basis":"harvester_set","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":"1ba831f456a905ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}