{"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/coordinating-filters-for-faster-deep-neural","title":"Coordinating Filters for Faster Deep Neural Networks","arxiv_id":"1703.09746","date":"2017-03-28","proceeding":"ICCV 2017 10","authors":["Wei Wen","Cong Xu","Chunpeng Wu","Yandan Wang","Yiran Chen","Hai Li"],"abstract":"Very large-scale Deep Neural Networks (DNNs) have achieved remarkable\nsuccesses in a large variety of computer vision tasks. However, the high\ncomputation intensity of DNNs makes it challenging to deploy these models on\nresource-limited systems. Some studies used low-rank approaches that\napproximate the filters by low-rank basis to accelerate the testing. Those\nworks directly decomposed the pre-trained DNNs by Low-Rank Approximations\n(LRA). How to train DNNs toward lower-rank space for more efficient DNNs,\nhowever, remains as an open area. To solve the issue, in this work, we propose\nForce Regularization, which uses attractive forces to enforce filters so as to\ncoordinate more weight information into lower-rank space. We mathematically and\nempirically verify that after applying our technique, standard LRA methods can\nreconstruct filters using much lower basis and thus result in faster DNNs. The\neffectiveness of our approach is comprehensively evaluated in ResNets, AlexNet,\nand GoogLeNet. In AlexNet, for example, Force Regularization gains 2x speedup\non modern GPU without accuracy loss and 4.05x speedup on CPU by paying small\naccuracy degradation. Moreover, Force Regularization better initializes the\nlow-rank DNNs such that the fine-tuning can converge faster toward higher\naccuracy. The obtained lower-rank DNNs can be further sparsified, proving that\nForce Regularization can be integrated with state-of-the-art sparsity-based\nacceleration methods. Source code is available in\nhttps://github.com/wenwei202/caffe","url_abs":"http://arxiv.org/abs/1703.09746v3","url_pdf":"http://arxiv.org/pdf/1703.09746v3.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":"coordinating-filters-for-faster-deep-neural","repo_url":"https://github.com/wenwei202/caffe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"coordinating-filters-for-faster-deep-neural","repo_url":"https://github.com/CSCI5470/testing-alexjohnny1207","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"coordinating-filters-for-faster-deep-neural","repo_url":"https://github.com/Lanselott/FM_caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"coordinating-filters-for-faster-deep-neural","repo_url":"https://github.com/2023-MindSpore-4/Code10/tree/main/googlenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"coordinating-filters-for-faster-deep-neural","repo_url":"https://github.com/MindSpore-paper-code-3/code10/tree/main/googlenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"googlenet","method_name":"GoogLeNet"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"inception-module","method_name":"Inception Module"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1703.09746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.09746"}},"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/MindSpore-paper-code-3/code10/tree/main/googlenet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CSCI5470/testing-alexjohnny1207","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wenwei202/caffe","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code10/tree/main/googlenet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Lanselott/FM_caffe","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"d1d197afa0f8be54","entry":"load_config","repo":"CSCI5470/testing-alexjohnny1207","repo_kind":"listed","path":"python/lowrank_approx.py","file_url":"https://github.com/CSCI5470/testing-alexjohnny1207/blob/HEAD/python/lowrank_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d1d197afa0f8be54"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}