{"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/asymmetric-non-local-neural-networks-for","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","arxiv_id":"1908.07678","date":"2019-08-21","proceeding":"ICCV 2019 10","authors":["Zhen Zhu","Mengde Xu","Song Bai","Tengteng Huang","Xiang Bai"],"abstract":"The non-local module works as a particularly useful technique for semantic segmentation while criticized for its prohibitive computation and GPU memory occupation. In this paper, we present Asymmetric Non-local Neural Network to semantic segmentation, which has two prominent components: Asymmetric Pyramid Non-local Block (APNB) and Asymmetric Fusion Non-local Block (AFNB). APNB leverages a pyramid sampling module into the non-local block to largely reduce the computation and memory consumption without sacrificing the performance. AFNB is adapted from APNB to fuse the features of different levels under a sufficient consideration of long range dependencies and thus considerably improves the performance. Extensive experiments on semantic segmentation benchmarks demonstrate the effectiveness and efficiency of our work. In particular, we report the state-of-the-art performance of 81.3 mIoU on the Cityscapes test set. For a 256x128 input, APNB is around 6 times faster than a non-local block on GPU while 28 times smaller in GPU running memory occupation. Code is available at: https://github.com/MendelXu/ANN.git.","url_abs":"https://arxiv.org/abs/1908.07678v5","url_pdf":"https://arxiv.org/pdf/1908.07678v5.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":"asymmetric-non-local-neural-networks-for","repo_url":"https://github.com/MendelXu/ANN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"asymmetric-non-local-neural-networks-for","repo_url":"https://github.com/donnyyou/torchcv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"asymmetric-non-local-neural-networks-for","repo_url":"https://github.com/wuyang556/ANNN_Paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"asymmetric-non-local-neural-networks-for","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"asymmetric-non-local-neural-networks-for","repo_url":"https://github.com/open-mmlab/mmsegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"non-local-block","method_name":"Non-Local Block"},{"method_slug":"non-local-operation","method_name":"Non-Local Operation"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"Asymmetric ALNN","rank_in_archive_order":194,"of":235,"metrics":{"Validation mIoU":"45.24"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"Asymmetric ALNN","rank_in_archive_order":82,"of":95,"metrics":{"mIoU":"45.24"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-coco-stuff-test","task":"Semantic Segmentation","dataset":"COCO-Stuff test","model":"Asymmetric ALNN","rank_in_archive_order":17,"of":21,"metrics":{"mIoU":"37.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"Asymmetric ALNN","rank_in_archive_order":45,"of":105,"metrics":{"Mean IoU (class)":"81.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-context","task":"Semantic Segmentation","dataset":"PASCAL Context","model":"Asymmetric ALNN","rank_in_archive_order":45,"of":66,"metrics":{"mIoU":"52.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.07678","atlas_url":"https://app.syntology.ai/?focus=1908.07678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07678"}},"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/donnyyou/torchcv","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MendelXu/ANN","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmsegmentation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wuyang556/ANNN_Paddle","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"7fd072abd1119b66","entry":"filter_blank","repo":"MendelXu/ANN","repo_kind":"official","path":"efficiency_statics/time_detail.py","file_url":"https://github.com/MendelXu/ANN/blob/HEAD/efficiency_statics/time_detail.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7fd072abd1119b66"}},{"code_sha256_prefix":"0ac25e4d5f6ee159","entry":"filter_end","repo":"MendelXu/ANN","repo_kind":"official","path":"efficiency_statics/time_detail.py","file_url":"https://github.com/MendelXu/ANN/blob/HEAD/efficiency_statics/time_detail.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ac25e4d5f6ee159"}},{"code_sha256_prefix":"bd8478b90ca0fa11","entry":"test","repo":"MendelXu/ANN","repo_kind":"official","path":"efficiency_statics/time_detail.py","file_url":"https://github.com/MendelXu/ANN/blob/HEAD/efficiency_statics/time_detail.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd8478b90ca0fa11"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}