{"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/dcfnet-deep-neural-network-with-decomposed","title":"DCFNet: Deep Neural Network with Decomposed Convolutional Filters","arxiv_id":"1802.04145","date":"2018-02-12","proceeding":"ICML 2018 7","authors":["Qiang Qiu","Xiuyuan Cheng","Robert Calderbank","Guillermo Sapiro"],"abstract":"Filters in a Convolutional Neural Network (CNN) contain model parameters\nlearned from enormous amounts of data. In this paper, we suggest to decompose\nconvolutional filters in CNN as a truncated expansion with pre-fixed bases,\nnamely the Decomposed Convolutional Filters network (DCFNet), where the\nexpansion coefficients remain learned from data. Such a structure not only\nreduces the number of trainable parameters and computation, but also imposes\nfilter regularity by bases truncation. Through extensive experiments, we\nconsistently observe that DCFNet maintains accuracy for image classification\ntasks with a significant reduction of model parameters, particularly with\nFourier-Bessel (FB) bases, and even with random bases. Theoretically, we\nanalyze the representation stability of DCFNet with respect to input\nvariations, and prove representation stability under generic assumptions on the\nexpansion coefficients. The analysis is consistent with the empirical\nobservations.","url_abs":"http://arxiv.org/abs/1802.04145v3","url_pdf":"http://arxiv.org/pdf/1802.04145v3.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":"dcfnet-deep-neural-network-with-decomposed","repo_url":"https://github.com/xycheng/DCFNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.04145","atlas_url":"https://app.syntology.ai/?focus=1802.04145","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":"1802.04145"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1802.04145\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1802.04145"},"call":"get_concepts_for_paper(arxiv_id=\"1802.04145\")"}],"by_repo":[{"repo":"xycheng/DCFNet","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":"fb861d69b9e4a607391ec5d870e748a9d38e18e6a966a1bda93e2ad942a9f455","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}