{"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/curriculumnet-weakly-supervised-learning-from","title":"CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images","arxiv_id":"1808.01097","date":"2018-08-03","proceeding":"ECCV 2018 9","authors":["Sheng Guo","Weilin Huang","Haozhi Zhang","Chenfan Zhuang","Dengke Dong","Matthew R. Scott","Dinglong Huang"],"abstract":"We present a simple yet efficient approach capable of training deep neural\nnetworks on large-scale weakly-supervised web images, which are crawled raw\nfrom the Internet by using text queries, without any human annotation. We\ndevelop a principled learning strategy by leveraging curriculum learning, with\nthe goal of handling a massive amount of noisy labels and data imbalance\neffectively. We design a new learning curriculum by measuring the complexity of\ndata using its distribution density in a feature space, and rank the complexity\nin an unsupervised manner. This allows for an efficient implementation of\ncurriculum learning on large-scale web images, resulting in a high-performance\nCNN model, where the negative impact of noisy labels is reduced substantially.\nImportantly, we show by experiments that those images with highly noisy labels\ncan surprisingly improve the generalization capability of the model, by serving\nas a manner of regularization. Our approaches obtain state-of-the-art\nperformance on four benchmarks: WebVision, ImageNet, Clothing-1M and Food-101.\nWith an ensemble of multiple models, we achieved a top-5 error rate of 5.2% on\nthe WebVision challenge for 1000-category classification. This result was the\ntop performance by a wide margin, outperforming second place by a nearly 50%\nrelative error rate. Code and models are available at:\nhttps://github.com/MalongTech/CurriculumNet .","url_abs":"http://arxiv.org/abs/1808.01097v4","url_pdf":"http://arxiv.org/pdf/1808.01097v4.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":"curriculumnet-weakly-supervised-learning-from","repo_url":"https://github.com/MalongTech/CurriculumNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"curriculumnet-weakly-supervised-learning-from","repo_url":"https://github.com/guoshengcv/CurriculumNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-clothing1m-using","task":"Image Classification","dataset":"Clothing1M (using clean data)","model":"CurriculumNet","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"81.5%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-webvision-1000","task":"Image Classification","dataset":"WebVision-1000","model":"CurriculumNet (InceptionResNet-v2)","rank_in_archive_order":2,"of":16,"metrics":{"Top-1 Accuracy":"79.3%","Top-5 Accuracy":"93.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-webvision-1000","task":"Image Classification","dataset":"WebVision-1000","model":"CurriculumNet (Inception-v2）","rank_in_archive_order":15,"of":16,"metrics":{"ImageNet Top-1 Accuracy":"64.8%","ImageNet Top-5 Accuracy":"84.9%","Top-1 Accuracy":"72.1%","Top-5 Accuracy":"89.2%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.01097","atlas_url":"https://app.syntology.ai/?focus=1808.01097","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":"1808.01097"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1808.01097\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1808.01097"},"call":"get_concepts_for_paper(arxiv_id=\"1808.01097\")"}],"by_repo":[{"repo":"MalongTech/CurriculumNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"guoshengcv/CurriculumNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ce2d27d8307166452302b57d9cf08b02c20ec9df7dfda8994962c5b4eb21b22b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}