{"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/exploring-non-contrastive-representation-1","title":"Learning Representation for Clustering via Prototype Scattering and Positive Sampling","arxiv_id":"2111.11821","date":"2021-11-23","proceeding":null,"authors":["Zhizhong Huang","Jie Chen","Junping Zhang","Hongming Shan"],"abstract":"Existing deep clustering methods rely on either contrastive or non-contrastive representation learning for downstream clustering task. Contrastive-based methods thanks to negative pairs learn uniform representations for clustering, in which negative pairs, however, may inevitably lead to the class collision issue and consequently compromise the clustering performance. Non-contrastive-based methods, on the other hand, avoid class collision issue, but the resulting non-uniform representations may cause the collapse of clustering. To enjoy the strengths of both worlds, this paper presents a novel end-to-end deep clustering method with prototype scattering and positive sampling, termed ProPos. Specifically, we first maximize the distance between prototypical representations, named prototype scattering loss, which improves the uniformity of representations. Second, we align one augmented view of instance with the sampled neighbors of another view -- assumed to be truly positive pair in the embedding space -- to improve the within-cluster compactness, termed positive sampling alignment. The strengths of ProPos are avoidable class collision issue, uniform representations, well-separated clusters, and within-cluster compactness. By optimizing ProPos in an end-to-end expectation-maximization framework, extensive experimental results demonstrate that ProPos achieves competing performance on moderate-scale clustering benchmark datasets and establishes new state-of-the-art performance on large-scale datasets. Source code is available at \\url{https://github.com/Hzzone/ProPos}.","url_abs":"https://arxiv.org/abs/2111.11821v2","url_pdf":"https://arxiv.org/pdf/2111.11821v2.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":"exploring-non-contrastive-representation-1","repo_url":"https://github.com/hzzone/propos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"task_slug":"image-clustering","task_name":"Image Clustering"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"byol","method_name":"BYOL"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-clustering-on-imagenet-10","task":"Image Clustering","dataset":"ImageNet-10","model":"ProPos*","rank_in_archive_order":4,"of":18,"metrics":{"ARI":"0.918","Accuracy":"0.962","Backbone":"ResNet-34","Image Size":"224","NMI":"0.908"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-imagenet-10","task":"Image Clustering","dataset":"ImageNet-10","model":"ProPos","rank_in_archive_order":9,"of":18,"metrics":{"ARI":"0.906","Accuracy":"0.956","Backbone":"ResNet-34","Image Size":"96","NMI":"0.896"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-imagenet-dog-15","task":"Image Clustering","dataset":"Imagenet-dog-15","model":"ProPos*","rank_in_archive_order":4,"of":20,"metrics":{"ARI":"0.675","Accuracy":"0.775","Backbone":"ResNet-34","Image Size":"224","NMI":"0.737"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-imagenet-dog-15","task":"Image Clustering","dataset":"Imagenet-dog-15","model":"ProPos","rank_in_archive_order":5,"of":20,"metrics":{"ARI":"0.627","Accuracy":"0.745","Backbone":"ResNet-34","Image Size":"96","NMI":"0.692"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.11821","atlas_url":"https://app.syntology.ai/?focus=2111.11821","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":"2111.11821"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.11821\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.11821"},"call":"get_concepts_for_paper(arxiv_id=\"2111.11821\")"}],"by_repo":[{"repo":"hzzone/propos","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":"ca6ffc6c4e54a3d1b66e3fb82e3743de838fef43e4de8b785d7956a2cbe1b701","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}