{"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/loss-functions-for-top-k-error-analysis-and","title":"Loss Functions for Top-k Error: Analysis and Insights","arxiv_id":"1512.00486","date":"2015-12-01","proceeding":"CVPR 2016 6","authors":["Maksim Lapin","Matthias Hein","Bernt Schiele"],"abstract":"In order to push the performance on realistic computer vision tasks, the\nnumber of classes in modern benchmark datasets has significantly increased in\nrecent years. This increase in the number of classes comes along with increased\nambiguity between the class labels, raising the question if top-1 error is the\nright performance measure. In this paper, we provide an extensive comparison\nand evaluation of established multiclass methods comparing their top-k\nperformance both from a practical as well as from a theoretical perspective.\nMoreover, we introduce novel top-k loss functions as modifications of the\nsoftmax and the multiclass SVM losses and provide efficient optimization\nschemes for them. In the experiments, we compare on various datasets all of the\nproposed and established methods for top-k error optimization. An interesting\ninsight of this paper is that the softmax loss yields competitive top-k\nperformance for all k simultaneously. For a specific top-k error, our new top-k\nlosses lead typically to further improvements while being faster to train than\nthe softmax.","url_abs":"http://arxiv.org/abs/1512.00486v2","url_pdf":"http://arxiv.org/pdf/1512.00486v2.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":"loss-functions-for-top-k-error-analysis-and","repo_url":"https://github.com/mlapin/libsdca","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"svm","method_name":"SVM"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1512.00486","atlas_url":"https://app.syntology.ai/?focus=1512.00486","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":"1512.00486"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1512.00486\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1512.00486"},"call":"get_concepts_for_paper(arxiv_id=\"1512.00486\")"}],"by_repo":[{"repo":"mlapin/libsdca","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":"30419e7249afd51fbde091a9ddc295ae3848034727b3e0aedb9292a7f763b95b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}