{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/feature-space-augmentation-for-long-tailed","title":"Feature Space Augmentation for Long-Tailed Data","arxiv_id":"2008.03673","date":"2020-08-09","proceeding":"ECCV 2020 8","authors":["Peng Chu","Xiao Bian","Shaopeng Liu","Haibin Ling"],"abstract":"Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. For example, a dataset can have a large number of under-represented classes and a few classes with more than sufficient data. However, a model to represent the dataset is usually expected to have reasonably homogeneous performances across classes. Introducing class-balanced loss and advanced methods on data re-sampling and augmentation are among the best practices to alleviate the data imbalance problem. However, the other part of the problem about the under-represented classes will have to rely on additional knowledge to recover the missing information. In this work, we present a novel approach to address the long-tailed problem by augmenting the under-represented classes in the feature space with the features learned from the classes with ample samples. In particular, we decompose the features of each class into a class-generic component and a class-specific component using class activation maps. Novel samples of under-represented classes are then generated on the fly during training stages by fusing the class-specific features from the under-represented classes with the class-generic features from confusing classes. Our results on different datasets such as iNaturalist, ImageNet-LT, Places-LT and a long-tailed version of CIFAR have shown the state of the art performances.","url_abs":"https://arxiv.org/abs/2008.03673v1","url_pdf":"https://arxiv.org/pdf/2008.03673v1.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":[],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNet-152","rank_in_archive_order":40,"of":60,"metrics":{"Top-1 Accuracy":"69.08%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNet-101","rank_in_archive_order":43,"of":60,"metrics":{"Top-1 Accuracy":"68.39%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNet-50","rank_in_archive_order":47,"of":60,"metrics":{"Top-1 Accuracy":"65.91%"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"Online Feature Augmentation","rank_in_archive_order":68,"of":69,"metrics":{"Top-1 Accuracy":"35.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"Online Feature Augmentation","rank_in_archive_order":26,"of":29,"metrics":{"Top-1 Accuracy":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"Online Feature Augmentation","rank_in_archive_order":43,"of":43,"metrics":{"Top-1 Accuracy":"65.9%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.03673","atlas_url":"https://app.syntology.ai/?focus=2008.03673","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2008.03673"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2008.03673\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2008.03673"},"call":"get_concepts_for_paper(arxiv_id=\"2008.03673\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"457aaaa75ed5bd142a44ca662881e2d4a59812e0c890797a7e3e4f13e02bfe98","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}