{"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/merge-or-not-learning-to-group-faces-via","title":"Merge or Not? Learning to Group Faces via Imitation Learning","arxiv_id":"1707.03986","date":"2017-07-13","proceeding":null,"authors":["Yue He","Kaidi Cao","Cheng Li","Chen Change Loy"],"abstract":"Given a large number of unlabeled face images, face grouping aims at\nclustering the images into individual identities present in the data. This task\nremains a challenging problem despite the remarkable capability of deep\nlearning approaches in learning face representation. In particular, grouping\nresults can still be egregious given profile faces and a large number of\nuninteresting faces and noisy detections. Often, a user needs to correct the\nerroneous grouping manually. In this study, we formulate a novel face grouping\nframework that learns clustering strategy from ground-truth simulated behavior.\nThis is achieved through imitation learning (a.k.a apprenticeship learning or\nlearning by watching) via inverse reinforcement learning (IRL). In contrast to\nexisting clustering approaches that group instances by similarity, our\nframework makes sequential decision to dynamically decide when to merge two\nface instances/groups driven by short- and long-term rewards. Extensive\nexperiments on three benchmark datasets show that our framework outperforms\nunsupervised and supervised baselines.","url_abs":"http://arxiv.org/abs/1707.03986v1","url_pdf":"http://arxiv.org/pdf/1707.03986v1.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":"merge-or-not-learning-to-group-faces-via","repo_url":"https://github.com/bj80heyue/Learning-to-Group","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.03986","atlas_url":"https://app.syntology.ai/?focus=1707.03986","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":"1707.03986"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1707.03986\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1707.03986"},"call":"get_concepts_for_paper(arxiv_id=\"1707.03986\")"}],"by_repo":[{"repo":"bj80heyue/Learning-to-Group","kind":"listed","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":"c382b51b314fd55ffae89e8ebbdee10f123989fe4710442ce6be623622764f6d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}