{"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/human-like-clustering-with-deep-convolutional","title":"Human-like Clustering with Deep Convolutional Neural Networks","arxiv_id":"1706.05048","date":"2017-06-15","proceeding":null,"authors":["Ali Borji","Aysegul Dundar"],"abstract":"Classification and clustering have been studied separately in machine\nlearning and computer vision. Inspired by the recent success of deep learning\nmodels in solving various vision problems (e.g., object recognition, semantic\nsegmentation) and the fact that humans serve as the gold standard in assessing\nclustering algorithms, here, we advocate for a unified treatment of the two\nproblems and suggest that hierarchical frameworks that progressively build\ncomplex patterns on top of the simpler ones (e.g., convolutional neural\nnetworks) offer a promising solution. We do not dwell much on the learning\nmechanisms in these frameworks as they are still a matter of debate, with\nrespect to biological constraints. Instead, we emphasize on the\ncompositionality of the real world structures and objects. In particular, we\nshow that CNNs, trained end to end using back propagation with noisy labels,\nare able to cluster data points belonging to several overlapping shapes, and do\nso much better than the state of the art algorithms. The main takeaway lesson\nfrom our study is that mechanisms of human vision, particularly the hierarchal\norganization of the visual ventral stream should be taken into account in\nclustering algorithms (e.g., for learning representations in an unsupervised\nmanner or with minimum supervision) to reach human level clustering\nperformance. This, by no means, suggests that other methods do not hold merits.\nFor example, methods relying on pairwise affinities (e.g., spectral clustering)\nhave been very successful in many scenarios but still fail in some cases (e.g.,\noverlapping clusters).","url_abs":"http://arxiv.org/abs/1706.05048v2","url_pdf":"http://arxiv.org/pdf/1706.05048v2.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":"human-like-clustering-with-deep-convolutional","repo_url":"https://github.com/Naghipourfar/Deep-Clustering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"Naghipourfar/Deep-Clustering","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":"e4e502b8eebcf07886179d25b15cb32771f6a1fbb3d84f2f35400989bebf0901","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}