{"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/disentangled-non-local-neural-networks","title":"Disentangled Non-Local Neural Networks","arxiv_id":"2006.06668","date":"2020-06-11","proceeding":"ECCV 2020 8","authors":["Minghao Yin","Zhuliang Yao","Yue Cao","Xiu Li","Zheng Zhang","Stephen Lin","Han Hu"],"abstract":"The non-local block is a popular module for strengthening the context modeling ability of a regular convolutional neural network. This paper first studies the non-local block in depth, where we find that its attention computation can be split into two terms, a whitened pairwise term accounting for the relationship between two pixels and a unary term representing the saliency of every pixel. We also observe that the two terms trained alone tend to model different visual clues, e.g. the whitened pairwise term learns within-region relationships while the unary term learns salient boundaries. However, the two terms are tightly coupled in the non-local block, which hinders the learning of each. Based on these findings, we present the disentangled non-local block, where the two terms are decoupled to facilitate learning for both terms. We demonstrate the effectiveness of the decoupled design on various tasks, such as semantic segmentation on Cityscapes, ADE20K and PASCAL Context, object detection on COCO, and action recognition on Kinetics.","url_abs":"https://arxiv.org/abs/2006.06668v2","url_pdf":"https://arxiv.org/pdf/2006.06668v2.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":"disentangled-non-local-neural-networks","repo_url":"https://github.com/Howal/DNL-Object-Detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"disentangled-non-local-neural-networks","repo_url":"https://github.com/yinmh17/DNL-Semantic-Segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"disentangled-non-local-neural-networks","repo_url":"https://github.com/JZPeterPan/k-gin","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"disentangled-non-local-neural-networks","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"disentangled-non-local-neural-networks","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":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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":"DNL","rank_in_archive_order":183,"of":235,"metrics":{"Validation mIoU":"45.97"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"DNL","rank_in_archive_order":75,"of":95,"metrics":{"mIoU":"45.97"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"DNL (coarse)","rank_in_archive_order":22,"of":105,"metrics":{"Mean IoU (class)":"83%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-dada-seg","task":"Semantic Segmentation","dataset":"DADA-seg","model":"DNL (ResNet-101)","rank_in_archive_order":22,"of":28,"metrics":{"mIoU":"19.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-densepass","task":"Semantic Segmentation","dataset":"DensePASS","model":"DNL (ResNet-101)","rank_in_archive_order":22,"of":36,"metrics":{"mIoU":"32.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-pascal-context","task":"Semantic Segmentation","dataset":"PASCAL Context","model":"DNL","rank_in_archive_order":30,"of":66,"metrics":{"mIoU":"55.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.06668","atlas_url":"https://app.syntology.ai/?focus=2006.06668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06668"}},"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/PaddlePaddle/PaddleSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JZPeterPan/k-gin","reach":{"status":"ok"}},{"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/Howal/DNL-Object-Detection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yinmh17/DNL-Semantic-Segmentation","reach":null}],"summary":{"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"17d55f21c366a359","entry":"str2bool","repo":"yinmh17/DNL-Semantic-Segmentation","repo_kind":"official","path":"datasets/seg/preprocess/cityscapes/cityscapes_seg_generator.py","file_url":"https://github.com/yinmh17/DNL-Semantic-Segmentation/blob/HEAD/datasets/seg/preprocess/cityscapes/cityscapes_seg_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17d55f21c366a359"}},{"code_sha256_prefix":"932080198381a3db","entry":"NonLocal2d_nowd","repo":"yinmh17/DNL-Semantic-Segmentation","repo_kind":"official","path":"model/seg/ops/nonlocal_block_nowd.py","file_url":"https://github.com/yinmh17/DNL-Semantic-Segmentation/blob/HEAD/model/seg/ops/nonlocal_block_nowd.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":"932080198381a3db"}},{"code_sha256_prefix":"2d92c27fc932f388","entry":"_NonLocalNd_nowd","repo":"yinmh17/DNL-Semantic-Segmentation","repo_kind":"official","path":"model/seg/ops/nonlocal_block_nowd.py","file_url":"https://github.com/yinmh17/DNL-Semantic-Segmentation/blob/HEAD/model/seg/ops/nonlocal_block_nowd.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":"2d92c27fc932f388"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}