{"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/mentornet-learning-data-driven-curriculum-for","title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","arxiv_id":"1712.05055","date":"2017-12-14","proceeding":"ICML 2018 7","authors":["Lu Jiang","Zhengyuan Zhou","Thomas Leung","Li-Jia Li","Li Fei-Fei"],"abstract":"Recent deep networks are capable of memorizing the entire data even when the\nlabels are completely random. To overcome the overfitting on corrupted labels,\nwe propose a novel technique of learning another neural network, called\nMentorNet, to supervise the training of the base deep networks, namely,\nStudentNet. During training, MentorNet provides a curriculum (sample weighting\nscheme) for StudentNet to focus on the sample the label of which is probably\ncorrect. Unlike the existing curriculum that is usually predefined by human\nexperts, MentorNet learns a data-driven curriculum dynamically with StudentNet.\nExperimental results demonstrate that our approach can significantly improve\nthe generalization performance of deep networks trained on corrupted training\ndata. Notably, to the best of our knowledge, we achieve the best-published\nresult on WebVision, a large benchmark containing 2.2 million images of\nreal-world noisy labels. The code are at https://github.com/google/mentornet","url_abs":"http://arxiv.org/abs/1712.05055v2","url_pdf":"http://arxiv.org/pdf/1712.05055v2.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":"mentornet-learning-data-driven-curriculum-for","repo_url":"https://github.com/google/mentornet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-webvision-1000","task":"Image Classification","dataset":"WebVision-1000","model":"MentorNet (InceptionResNet-V2)","rank_in_archive_order":16,"of":16,"metrics":{"ImageNet Top-1 Accuracy":"62.5%","ImageNet Top-5 Accuracy":"83.0%","Top-1 Accuracy":"70.8%","Top-5 Accuracy":"88.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"MentorNet (Inception-ResNet-v2)","rank_in_archive_order":44,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"63.8","ImageNet Top-5 Accuracy":"85.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.05055","atlas_url":"https://app.syntology.ai/?focus=1712.05055","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":"1712.05055"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1712.05055\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1712.05055"},"call":"get_concepts_for_paper(arxiv_id=\"1712.05055\")"}],"by_repo":[{"repo":"google/mentornet","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":"2f4b09daf11677598114f5f1b220435c5e1673e278163b0278f35361ab82289a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}