{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/linkage-based-face-clustering-via-graph","title":"Linkage Based Face Clustering via Graph Convolution Network","arxiv_id":"1903.11306","date":"2019-03-27","proceeding":"CVPR 2019 6","authors":["Zhongdao Wang","Liang Zheng","Ya-Li Li","Shengjin Wang"],"abstract":"In this paper, we present an accurate and scalable approach to the face\nclustering task. We aim at grouping a set of faces by their potential\nidentities. We formulate this task as a link prediction problem: a link exists\nbetween two faces if they are of the same identity. The key idea is that we\nfind the local context in the feature space around an instance (face) contains\nrich information about the linkage relationship between this instance and its\nneighbors. By constructing sub-graphs around each instance as input data, which\ndepict the local context, we utilize the graph convolution network (GCN) to\nperform reasoning and infer the likelihood of linkage between pairs in the\nsub-graphs. Experiments show that our method is more robust to the complex\ndistribution of faces than conventional methods, yielding favorably comparable\nresults to state-of-the-art methods on standard face clustering benchmarks, and\nis scalable to large datasets. Furthermore, we show that the proposed method\ndoes not need the number of clusters as prior, is aware of noises and outliers,\nand can be extended to a multi-view version for more accurate clustering\naccuracy.","url_abs":"http://arxiv.org/abs/1903.11306v3","url_pdf":"http://arxiv.org/pdf/1903.11306v3.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":"linkage-based-face-clustering-via-graph","repo_url":"https://github.com/Zhongdao/gcn_clustering","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"linkage-based-face-clustering-via-graph","repo_url":"https://github.com/espectre/GCNs_on_imbalanced_datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"linkage-based-face-clustering-via-graph","repo_url":"https://github.com/xiaoxiong74/face-cluster-by-infomap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"linkage-based-face-clustering-via-graph","repo_url":"https://github.com/yl-1993/learn-to-cluster","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"face-clustering","task_name":"Face Clustering"},{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.11306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.11306"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/espectre/GCNs_on_imbalanced_datasets","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Zhongdao/gcn_clustering","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaoxiong74/face-cluster-by-infomap","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yl-1993/learn-to-cluster","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7d6e263caea8e963","entry":"read_json","repo":"Zhongdao/gcn_clustering","repo_kind":"official","path":"utils/serialization.py","file_url":"https://github.com/Zhongdao/gcn_clustering/blob/HEAD/utils/serialization.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"code_sha256_prefix":"baec6b55b45c9eb9","entry":"bcubed","repo":"Zhongdao/gcn_clustering","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/Zhongdao/gcn_clustering/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"baec6b55b45c9eb9"}},{"code_sha256_prefix":"0a0636ddfda3d370","entry":"contingency_matrix","repo":"Zhongdao/gcn_clustering","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/Zhongdao/gcn_clustering/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a0636ddfda3d370"}},{"code_sha256_prefix":"43879b49d0ac5101","entry":"copy_state_dict","repo":"Zhongdao/gcn_clustering","repo_kind":"official","path":"utils/serialization.py","file_url":"https://github.com/Zhongdao/gcn_clustering/blob/HEAD/utils/serialization.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43879b49d0ac5101"}},{"code_sha256_prefix":"31a605667128ee34","entry":"load_checkpoint","repo":"Zhongdao/gcn_clustering","repo_kind":"official","path":"utils/serialization.py","file_url":"https://github.com/Zhongdao/gcn_clustering/blob/HEAD/utils/serialization.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31a605667128ee34"}},{"code_sha256_prefix":"3d00bb6d1cb957a0","entry":"norm","repo":"Zhongdao/gcn_clustering","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/Zhongdao/gcn_clustering/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d00bb6d1cb957a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}