{"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/improving-image-clustering-with-multiple","title":"Improving Image Clustering With Multiple Pretrained CNN Feature Extractors","arxiv_id":"1807.07760","date":"2018-07-20","proceeding":null,"authors":["Joris Guérin","Byron Boots"],"abstract":"For many image clustering problems, replacing raw image data with features\nextracted by a pretrained convolutional neural network (CNN), leads to better\nclustering performance. However, the specific features extracted, and, by\nextension, the selected CNN architecture, can have a major impact on the\nclustering results. In practice, this crucial design choice is often decided\narbitrarily due to the impossibility of using cross-validation with\nunsupervised learning problems. However, information contained in the different\npretrained CNN architectures may be complementary, even when pretrained on the\nsame data. To improve clustering performance, we rephrase the image clustering\nproblem as a multi-view clustering (MVC) problem that considers multiple\ndifferent pretrained feature extractors as different \"views\" of the same data.\nWe then propose a multi-input neural network architecture that is trained\nend-to-end to solve the MVC problem effectively. Our experimental results,\nconducted on three different natural image datasets, show that: 1. using\nmultiple pretrained CNNs jointly as feature extractors improves image\nclustering; 2. using an end-to-end approach improves MVC; and 3. combining both\nproduces state-of-the-art results for the problem of image clustering.","url_abs":"http://arxiv.org/abs/1807.07760v1","url_pdf":"http://arxiv.org/pdf/1807.07760v1.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":"improving-image-clustering-with-multiple","repo_url":"https://github.com/MrGrayCode/Clustering-CNN-Features","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"image-clustering","task_name":"Image Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.07760","atlas_url":"https://app.syntology.ai/?focus=1807.07760","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":"1807.07760"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1807.07760\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1807.07760"},"call":"get_concepts_for_paper(arxiv_id=\"1807.07760\")"}],"by_repo":[{"repo":"MrGrayCode/Clustering-CNN-Features","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":"d0b875a423bd6126c9ac5419ec73148b1179ae73aba0fbdad7a966adcb09ebe2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}