{"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/manipulating-identical-filter-redundancy-for","title":"Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN","arxiv_id":"2107.14444","date":"2021-07-30","proceeding":null,"authors":["Xiaohan Ding","Tianxiang Hao","Jungong Han","Yuchen Guo","Guiguang Ding"],"abstract":"The existence of redundancy in Convolutional Neural Networks (CNNs) enables us to remove some filters/channels with acceptable performance drops. However, the training objective of CNNs usually tends to minimize an accuracy-related loss function without any attention paid to the redundancy, making the redundancy distribute randomly on all the filters, such that removing any of them may trigger information loss and accuracy drop, necessitating a following finetuning step for recovery. In this paper, we propose to manipulate the redundancy during training to facilitate network pruning. To this end, we propose a novel Centripetal SGD (C-SGD) to make some filters identical, resulting in ideal redundancy patterns, as such filters become purely redundant due to their duplicates; hence removing them does not harm the network. As shown on CIFAR and ImageNet, C-SGD delivers better performance because the redundancy is better organized, compared to the existing methods. The efficiency also characterizes C-SGD because it is as fast as regular SGD, requires no finetuning, and can be conducted simultaneously on all the layers even in very deep CNNs. Besides, C-SGD can improve the accuracy of CNNs by first training a model with the same architecture but wider layers then squeezing it into the original width.","url_abs":"https://arxiv.org/abs/2107.14444v1","url_pdf":"https://arxiv.org/pdf/2107.14444v1.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":"manipulating-identical-filter-redundancy-for","repo_url":"https://github.com/DingXiaoH/Centripetal-SGD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"manipulating-identical-filter-redundancy-for","repo_url":"https://github.com/ShawnDing1994/Centripetal-SGD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.14444","atlas_url":"https://app.syntology.ai/?focus=2107.14444","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":"2107.14444"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2107.14444\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2107.14444"},"call":"get_concepts_for_paper(arxiv_id=\"2107.14444\")"}],"by_repo":[{"repo":"DingXiaoH/Centripetal-SGD","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ShawnDing1994/Centripetal-SGD","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.12778"],"harvested_for_calls":[{"arxiv_id":"1909.12778","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.12778"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.12778\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"7684c08cbabec9f8509d49f7d3bf8bac192cedbd5f3c3076a4f0621483f849a0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}