{"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/revisiting-dynamic-convolution-via-matrix-1","title":"Revisiting Dynamic Convolution via Matrix Decomposition","arxiv_id":"2103.08756","date":"2021-03-15","proceeding":"ICLR 2021 1","authors":["Yunsheng Li","Yinpeng Chen","Xiyang Dai","Mengchen Liu","Dongdong Chen","Ye Yu","Lu Yuan","Zicheng Liu","Mei Chen","Nuno Vasconcelos"],"abstract":"Recent research in dynamic convolution shows substantial performance boost for efficient CNNs, due to the adaptive aggregation of K static convolution kernels. It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention and static convolution kernels is challenging. In this paper, we revisit it from a new perspective of matrix decomposition and reveal the key issue is that dynamic convolution applies dynamic attention over channel groups after projecting into a higher dimensional latent space. To address this issue, we propose dynamic channel fusion to replace dynamic attention over channel groups. Dynamic channel fusion not only enables significant dimension reduction of the latent space, but also mitigates the joint optimization difficulty. As a result, our method is easier to train and requires significantly fewer parameters without sacrificing accuracy. Source code is at https://github.com/liyunsheng13/dcd.","url_abs":"https://arxiv.org/abs/2103.08756v1","url_pdf":"https://arxiv.org/pdf/2103.08756v1.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":"revisiting-dynamic-convolution-via-matrix-1","repo_url":"https://github.com/liyunsheng13/dcd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.08756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.08756"}},"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":"deterministic:regex_extraction","url":"https://github.com/liyunsheng13/dcd","reach":null}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":6,"samples":[{"code_sha256_prefix":"ab619020854bd9ad","entry":"DYModule","repo":"liyunsheng13/dcd","repo_kind":"official","path":"models/imagenet/mobilenetv2_dcd.py","file_url":"https://github.com/liyunsheng13/dcd/blob/HEAD/models/imagenet/mobilenetv2_dcd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ab619020854bd9ad"}},{"code_sha256_prefix":"48151cd414b0a381","entry":"Hsigmoid","repo":"liyunsheng13/dcd","repo_kind":"official","path":"models/imagenet/mobilenetv2_dcd.py","file_url":"https://github.com/liyunsheng13/dcd/blob/HEAD/models/imagenet/mobilenetv2_dcd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"48151cd414b0a381"}},{"code_sha256_prefix":"056bc283f07f029a","entry":"SEModule_small","repo":"liyunsheng13/dcd","repo_kind":"official","path":"models/imagenet/mobilenetv2_dcd.py","file_url":"https://github.com/liyunsheng13/dcd/blob/HEAD/models/imagenet/mobilenetv2_dcd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"056bc283f07f029a"}},{"code_sha256_prefix":"138525ef5b7a7291","entry":"conv3x3","repo":"liyunsheng13/dcd","repo_kind":"official","path":"models/imagenet/resnet_dcd.py","file_url":"https://github.com/liyunsheng13/dcd/blob/HEAD/models/imagenet/resnet_dcd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"138525ef5b7a7291"}},{"code_sha256_prefix":"9bae3f6c95a2da30","entry":"resnet18_dcd","repo":"liyunsheng13/dcd","repo_kind":"official","path":"models/imagenet/resnet_dcd.py","file_url":"https://github.com/liyunsheng13/dcd/blob/HEAD/models/imagenet/resnet_dcd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9bae3f6c95a2da30"}},{"code_sha256_prefix":"6a6237c34845afb3","entry":"resnet34_dcd","repo":"liyunsheng13/dcd","repo_kind":"official","path":"models/imagenet/resnet_dcd.py","file_url":"https://github.com/liyunsheng13/dcd/blob/HEAD/models/imagenet/resnet_dcd.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6a6237c34845afb3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}