{"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/max-margin-class-imbalanced-learning-with","title":"Max-margin Class Imbalanced Learning with Gaussian Affinity","arxiv_id":"1901.07711","date":"2019-01-23","proceeding":null,"authors":["Munawar Hayat","Salman Khan","Waqas Zamir","Jianbing Shen","Ling Shao"],"abstract":"Real-world object classes appear in imbalanced ratios. This poses a\nsignificant challenge for classifiers which get biased towards frequent\nclasses. We hypothesize that improving the generalization capability of a\nclassifier should improve learning on imbalanced datasets. Here, we introduce\nthe first hybrid loss function that jointly performs classification and\nclustering in a single formulation. Our approach is based on an `affinity\nmeasure' in Euclidean space that leads to the following benefits: (1) direct\nenforcement of maximum margin constraints on classification boundaries, (2) a\ntractable way to ensure uniformly spaced and equidistant cluster centers, (3)\nflexibility to learn multiple class prototypes to support diversity and\ndiscriminability in feature space. Our extensive experiments demonstrate the\nsignificant performance improvements on visual classification and verification\ntasks on multiple imbalanced datasets. The proposed loss can easily be plugged\nin any deep architecture as a differentiable block and demonstrates robustness\nagainst different levels of data imbalance and corrupted labels.","url_abs":"http://arxiv.org/abs/1901.07711v1","url_pdf":"http://arxiv.org/pdf/1901.07711v1.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":"max-margin-class-imbalanced-learning-with","repo_url":"https://github.com/koshian2/affinity-loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.07711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07711"}},"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/koshian2/affinity-loss","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"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":"b7570d6a1012f1c6","entry":"step_decay","repo":"koshian2/affinity-loss","repo_kind":"listed","path":"cnn_mnist_affinity.py","file_url":"https://github.com/koshian2/affinity-loss/blob/HEAD/cnn_mnist_affinity.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7570d6a1012f1c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}