{"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/rethinking-feature-discrimination-and","title":"Rethinking Feature Discrimination and Polymerization for Large-scale Recognition","arxiv_id":"1710.00870","date":"2017-10-02","proceeding":null,"authors":["Yu Liu","Hongyang Li","Xiaogang Wang"],"abstract":"Feature matters. How to train a deep network to acquire discriminative\nfeatures across categories and polymerized features within classes has always\nbeen at the core of many computer vision tasks, specially for large-scale\nrecognition systems where test identities are unseen during training and the\nnumber of classes could be at million scale. In this paper, we address this\nproblem based on the simple intuition that the cosine distance of features in\nhigh-dimensional space should be close enough within one class and far away\nacross categories. To this end, we proposed the congenerous cosine (COCO)\nalgorithm to simultaneously optimize the cosine similarity among data. It\ninherits the softmax property to make inter-class features discriminative as\nwell as shares the idea of class centroid in metric learning. Unlike previous\nwork where the center is a temporal, statistical variable within one mini-batch\nduring training, the formulated centroid is responsible for clustering\ninner-class features to enforce them polymerized around the network truncus.\nCOCO is bundled with discriminative training and learned end-to-end with stable\nconvergence. Experiments on five benchmarks have been extensively conducted to\nverify the effectiveness of our approach on both small-scale classification\ntask and large-scale human recognition problem.","url_abs":"http://arxiv.org/abs/1710.00870v2","url_pdf":"http://arxiv.org/pdf/1710.00870v2.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":"rethinking-feature-discrimination-and","repo_url":"https://github.com/sciencefans/coco_loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.00870","atlas_url":"https://app.syntology.ai/?focus=1710.00870","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":"1710.00870"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1710.00870\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1710.00870"},"call":"get_concepts_for_paper(arxiv_id=\"1710.00870\")"}],"by_repo":[{"repo":"sciencefans/coco_loss","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":"a31d4f3dc0bc5d7f2830030115355aab690c16029578a5dba6af92df1e4c6e20","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}