{"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/classes-are-not-equal-an-empirical-study-on","title":"Classes Are Not Equal: An Empirical Study on Image Recognition Fairness","arxiv_id":"2402.18133","date":"2024-02-28","proceeding":"CVPR 2024 1","authors":["Jiequan Cui","Beier Zhu","Xin Wen","Xiaojuan Qi","Bei Yu","Hanwang Zhang"],"abstract":"In this paper, we present an empirical study on image recognition fairness, i.e., extreme class accuracy disparity on balanced data like ImageNet. We experimentally demonstrate that classes are not equal and the fairness issue is prevalent for image classification models across various datasets, network architectures, and model capacities. Moreover, several intriguing properties of fairness are identified. First, the unfairness lies in problematic representation rather than classifier bias. Second, with the proposed concept of Model Prediction Bias, we investigate the origins of problematic representation during optimization. Our findings reveal that models tend to exhibit greater prediction biases for classes that are more challenging to recognize. It means that more other classes will be confused with harder classes. Then the False Positives (FPs) will dominate the learning in optimization, thus leading to their poor accuracy. Further, we conclude that data augmentation and representation learning algorithms improve overall performance by promoting fairness to some degree in image classification. The Code is available at https://github.com/dvlab-research/Parametric-Contrastive-Learning.","url_abs":"https://arxiv.org/abs/2402.18133v2","url_pdf":"https://arxiv.org/pdf/2402.18133v2.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":"classes-are-not-equal-an-empirical-study-on","repo_url":"https://github.com/dvlab-research/parametric-contrastive-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.18133","atlas_url":"https://app.syntology.ai/?focus=2402.18133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18133"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dvlab-research/parametric-contrastive-learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"b793b278a771fd52","entry":"accuracy","repo":"dvlab-research/parametric-contrastive-learning","repo_kind":"official","path":"GPaCo/LT/paco_imagenet.py","file_url":"https://github.com/dvlab-research/parametric-contrastive-learning/blob/HEAD/GPaCo/LT/paco_imagenet.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b793b278a771fd52"}},{"code_sha256_prefix":"b4e3904ffc1e943d","entry":"compute_mce","repo":"dvlab-research/parametric-contrastive-learning","repo_kind":"official","path":"GPaCo/LT/paco_imagenet.py","file_url":"https://github.com/dvlab-research/parametric-contrastive-learning/blob/HEAD/GPaCo/LT/paco_imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4e3904ffc1e943d"}},{"code_sha256_prefix":"13eac6ce75be2d11","entry":"validate","repo":"dvlab-research/parametric-contrastive-learning","repo_kind":"official","path":"GPaCo/LT/paco_imagenet.py","file_url":"https://github.com/dvlab-research/parametric-contrastive-learning/blob/HEAD/GPaCo/LT/paco_imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13eac6ce75be2d11"}},{"code_sha256_prefix":"a27000d4fe943463","entry":"test","repo":"dvlab-research/parametric-contrastive-learning","repo_kind":"official","path":"GPaCo/MAE-ViTs/engine_finetune_paco.py","file_url":"https://github.com/dvlab-research/parametric-contrastive-learning/blob/HEAD/GPaCo/MAE-ViTs/engine_finetune_paco.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":"a27000d4fe943463"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}