{"url":"/sota/image-classification-on-clothing1m-using","task":{"name":"Image Classification","url":"/task/image-classification","note":null},"dataset":{"name":"Clothing1M (using clean data)","url":"/dataset/clothing1m"},"category":"Computer Vision","categories":["Adversarial","Computer Vision"],"category_note":null,"description":"**Image Classification** is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike [object detection](/task/object-detection), which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as [image retrieval](/task/image-retrieval), which also involves finding similar images in a large database.\r\n\r\n\r\n<span class=\"description-source\">Source: [Metamorphic Testing for Object Detection Systems ](https://arxiv.org/abs/1912.12162)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":9,"rows_with_code":9,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"CurriculumNet","metrics":{"Accuracy":"81.5%"},"uses_additional_data":true,"paper_date":"2018-08-03","paper":"/paper/curriculumnet-weakly-supervised-learning-from","paper_url":"http://arxiv.org/abs/1808.01097v4","paper_title":"CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images","code":"https://github.com/MalongTech/CurriculumNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"Forward","metrics":{"Accuracy":"80.27"},"uses_additional_data":true,"paper_date":"2016-09-13","paper":"/paper/making-deep-neural-networks-robust-to-label","paper_url":"http://arxiv.org/abs/1609.03683v2","paper_title":"Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach","code":"https://github.com/yikun2019/PENCIL","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"CleanNet w_soft","metrics":{"Accuracy":"79.90"},"uses_additional_data":true,"paper_date":"2017-11-20","paper":"/paper/cleannet-transfer-learning-for-scalable-image","paper_url":"http://arxiv.org/abs/1711.07131v2","paper_title":"CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise","code":"https://github.com/kuanghuei/clean-net","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"EMLC (k=1)","metrics":{"Accuracy":"79.35%"},"uses_additional_data":false,"paper_date":"2023-05-22","paper":"/paper/enhanced-meta-label-correction-for-coping","paper_url":"https://arxiv.org/abs/2305.12961v2","paper_title":"Enhanced Meta Label Correction for Coping with Label Corruption","code":"https://github.com/MitchellKT/Enhanced-Meta-Label-Correction","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"DMLP-DivideMix","metrics":{"Accuracy":"78.23%"},"uses_additional_data":false,"paper_date":"2023-02-14","paper":"/paper/learning-from-noisy-labels-with-decoupled","paper_url":"https://arxiv.org/abs/2302.06810v3","paper_title":"Learning from Noisy Labels with Decoupled Meta Label Purifier","code":"https://github.com/yuanpengtu/DMLP","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"FasTEN","metrics":{"Accuracy":"77.83%"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/learning-with-noisy-labels-by-efficient-1","paper_url":"https://arxiv.org/abs/2111.14932v2","paper_title":"Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection","code":"https://github.com/hyperconnect/fasten","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"PUDistill","metrics":{"Accuracy":"77.70"},"uses_additional_data":true,"paper_date":"2021-05-27","paper":"/paper/training-classifiers-that-are-universally","paper_url":"https://arxiv.org/abs/2105.13892v1","paper_title":"Training Classifiers that are Universally Robust to All Label Noise Levels","code":"https://github.com/Xu-Jingyi/PUDistill","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"L2B (ResNet-18)","metrics":{"Accuracy":"77.5 ± 0.2%"},"uses_additional_data":true,"paper_date":"2022-02-09","paper":"/paper/learning-to-bootstrap-for-combating-label","paper_url":"https://arxiv.org/abs/2202.04291v2","paper_title":"L2B: Learning to Bootstrap Robust Models for Combating Label Noise","code":"https://github.com/yuyinzhou/l2b","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"MLC","metrics":{"Accuracy":"75.78%"},"uses_additional_data":true,"paper_date":"2019-11-10","paper":"/paper/meta-label-correction-for-learning-with-weak-1","paper_url":"https://arxiv.org/abs/1911.03809v2","paper_title":"Meta Label Correction for Noisy Label Learning","code":"https://github.com/microsoft/mlc","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":11,"n_samples":13,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":11,"n_samples":13,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}