{"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/acnet-strengthening-the-kernel-skeletons-for","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","arxiv_id":"1908.03930","date":"2019-08-11","proceeding":"ICCV 2019 10","authors":["Xiaohan Ding","Yuchen Guo","Guiguang Ding","Jungong Han"],"abstract":"As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous GPU hours, the research community is soliciting the architecture-neutral CNN structures, which can be easily plugged into multiple mature architectures to improve the performance on our real-world applications. We propose Asymmetric Convolution Block (ACB), an architecture-neutral structure as a CNN building block, which uses 1D asymmetric convolutions to strengthen the square convolution kernels. For an off-the-shelf architecture, we replace the standard square-kernel convolutional layers with ACBs to construct an Asymmetric Convolutional Network (ACNet), which can be trained to reach a higher level of accuracy. After training, we equivalently convert the ACNet into the same original architecture, thus requiring no extra computations anymore. We have observed that ACNet can improve the performance of various models on CIFAR and ImageNet by a clear margin. Through further experiments, we attribute the effectiveness of ACB to its capability of enhancing the model's robustness to rotational distortions and strengthening the central skeleton parts of square convolution kernels.","url_abs":"https://arxiv.org/abs/1908.03930v3","url_pdf":"https://arxiv.org/pdf/1908.03930v3.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":"acnet-strengthening-the-kernel-skeletons-for","repo_url":"https://github.com/ShawnDing1994/ACNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"acnet-strengthening-the-kernel-skeletons-for","repo_url":"https://github.com/CXYCarson/TF_AcBlock","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"acnet-strengthening-the-kernel-skeletons-for","repo_url":"https://github.com/amithenig/kflo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"acnet-strengthening-the-kernel-skeletons-for","repo_url":"https://github.com/xdhe1216/ACNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"acnet-strengthening-the-kernel-skeletons-for","repo_url":"https://github.com/PaddlePaddle/PaddleClas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":null,"task_name":"GPU"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.03930","atlas_url":"https://app.syntology.ai/?focus=1908.03930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03930"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/xdhe1216/ACNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleClas","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShawnDing1994/ACNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amithenig/kflo","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CXYCarson/TF_AcBlock","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"repositories":2}},"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":"ee7045377b07d71d","entry":"diff_model","repo":"xdhe1216/ACNet","repo_kind":"listed","path":"acnet_repvgg_dbb_block_utils.py","file_url":"https://github.com/xdhe1216/ACNet/blob/HEAD/acnet_repvgg_dbb_block_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ee7045377b07d71d"}},{"code_sha256_prefix":"c21cc033da8f070a","entry":"AC_Block","repo":"CXYCarson/TF_AcBlock","repo_kind":"listed","path":"Ac_Block_utils.py","file_url":"https://github.com/CXYCarson/TF_AcBlock/blob/HEAD/Ac_Block_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c21cc033da8f070a"}},{"code_sha256_prefix":"60355ac746e76938","entry":"kernel_fusion","repo":"CXYCarson/TF_AcBlock","repo_kind":"listed","path":"Ac_Block_utils.py","file_url":"https://github.com/CXYCarson/TF_AcBlock/blob/HEAD/Ac_Block_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60355ac746e76938"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}