{"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/mice-mixture-of-contrastive-experts-for-1","title":"MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering","arxiv_id":"2105.01899","date":"2021-05-05","proceeding":"ICLR 2021 1","authors":["Tsung Wei Tsai","Chongxuan Li","Jun Zhu"],"abstract":"We present Mixture of Contrastive Experts (MiCE), a unified probabilistic clustering framework that simultaneously exploits the discriminative representations learned by contrastive learning and the semantic structures captured by a latent mixture model. Motivated by the mixture of experts, MiCE employs a gating function to partition an unlabeled dataset into subsets according to the latent semantics and multiple experts to discriminate distinct subsets of instances assigned to them in a contrastive learning manner. To solve the nontrivial inference and learning problems caused by the latent variables, we further develop a scalable variant of the Expectation-Maximization (EM) algorithm for MiCE and provide proof of the convergence. Empirically, we evaluate the clustering performance of MiCE on four widely adopted natural image datasets. MiCE achieves significantly better results than various previous methods and a strong contrastive learning baseline.","url_abs":"https://arxiv.org/abs/2105.01899v1","url_pdf":"https://arxiv.org/pdf/2105.01899v1.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":"mice-mixture-of-contrastive-experts-for-1","repo_url":"https://github.com/TsungWeiTsai/MiCE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"image-clustering","task_name":"Image Clustering"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-clustering-on-imagenet-dog-15","task":"Image Clustering","dataset":"Imagenet-dog-15","model":"MiCE","rank_in_archive_order":11,"of":20,"metrics":{"ARI":"0.286","Accuracy":"0.439","Image Size":"96","NMI":"0.423"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-stl-10","task":"Image Clustering","dataset":"STL-10","model":"MiCE","rank_in_archive_order":18,"of":29,"metrics":{"Accuracy":"0.752","Backbone":"ResNet-34","NMI":"0.635","Train Split":"Train+Test"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.01899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01899"}},"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/TsungWeiTsai/MiCE","reach":null}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"c7487c9a791362ec","entry":"MiCE_ELBO","repo":"TsungWeiTsai/MiCE","repo_kind":"official","path":"ELBO.py","file_url":"https://github.com/TsungWeiTsai/MiCE/blob/HEAD/ELBO.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c7487c9a791362ec"}},{"code_sha256_prefix":"c92007fbc20fd70e","entry":"get_MiCE_performance","repo":"TsungWeiTsai/MiCE","repo_kind":"official","path":"eval_MiCE.py","file_url":"https://github.com/TsungWeiTsai/MiCE/blob/HEAD/eval_MiCE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c92007fbc20fd70e"}},{"code_sha256_prefix":"720443a9d611f906","entry":"train_MiCE","repo":"TsungWeiTsai/MiCE","repo_kind":"official","path":"train_MiCE.py","file_url":"https://github.com/TsungWeiTsai/MiCE/blob/HEAD/train_MiCE.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"720443a9d611f906"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}