{"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/axial-deeplab-stand-alone-axial-attention-for","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","arxiv_id":"2003.07853","date":"2020-03-17","proceeding":"ECCV 2020 8","authors":["Huiyu Wang","Yukun Zhu","Bradley Green","Hartwig Adam","Alan Yuille","Liang-Chieh Chen"],"abstract":"Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prove it possible to stack self-attention layers to obtain a fully attentional network by restricting the attention to a local region. In this paper, we attempt to remove this constraint by factorizing 2D self-attention into two 1D self-attentions. This reduces computation complexity and allows performing attention within a larger or even global region. In companion, we also propose a position-sensitive self-attention design. Combining both yields our position-sensitive axial-attention layer, a novel building block that one could stack to form axial-attention models for image classification and dense prediction. We demonstrate the effectiveness of our model on four large-scale datasets. In particular, our model outperforms all existing stand-alone self-attention models on ImageNet. Our Axial-DeepLab improves 2.8% PQ over bottom-up state-of-the-art on COCO test-dev. This previous state-of-the-art is attained by our small variant that is 3.8x parameter-efficient and 27x computation-efficient. Axial-DeepLab also achieves state-of-the-art results on Mapillary Vistas and Cityscapes.","url_abs":"https://arxiv.org/abs/2003.07853v2","url_pdf":"https://arxiv.org/pdf/2003.07853v2.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":"axial-deeplab-stand-alone-axial-attention-for","repo_url":"https://github.com/google-research/deeplab2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"axial-deeplab-stand-alone-axial-attention-for","repo_url":"https://github.com/csrhddlam/axial-deeplab","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"axial-deeplab-stand-alone-axial-attention-for","repo_url":"https://github.com/MartinGer/Stand-Alone-Axial-Attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"axial-deeplab-stand-alone-axial-attention-for","repo_url":"https://github.com/xiaofeng94/gmflownet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"axial-deeplab-stand-alone-axial-attention-for","repo_url":"https://github.com/The-AI-Summer/self_attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":null,"task_name":"Position"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/panoptic-segmentation-on-coco-minival","task":"Panoptic Segmentation","dataset":"COCO minival","model":"Axial-DeepLab-L (multi-scale)","rank_in_archive_order":28,"of":31,"metrics":{"PQ":"43.9"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-minival","task":"Panoptic Segmentation","dataset":"COCO minival","model":"Axial-DeepLab-L (single-scale)","rank_in_archive_order":29,"of":31,"metrics":{"PQ":"43.4","PQst":"35.6","PQth":"48.5"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-minival","task":"Panoptic Segmentation","dataset":"COCO minival","model":"Axial-DeepLab-L(multi-scale)","rank_in_archive_order":30,"of":31,"metrics":{"PQst":"36.8","PQth":"48.6"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"Axial-DeepLab-L (multi-scale)","rank_in_archive_order":28,"of":38,"metrics":{"PQ":"44.2","PQst":"36.8","PQth":"49.2"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"Axial-DeepLab-L","rank_in_archive_order":29,"of":38,"metrics":{"PQ":"43.6","PQst":"35.6","PQth":"48.9"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-test","task":"Panoptic Segmentation","dataset":"Cityscapes test","model":"Axial-DeepLab-XL (Mapillary Vistas, multi-scale)","rank_in_archive_order":4,"of":10,"metrics":{"PQ":"66.6"},"uses_additional_data":true},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"Axial-DeepLab-XL (Mapillary Vistas, multi-scale)","rank_in_archive_order":5,"of":37,"metrics":{"AP":" 44.2","PQ":"68.5","mIoU":"84.6"},"uses_additional_data":true},{"leaderboard":"/sota/panoptic-segmentation-on-mapillary-val","task":"Panoptic Segmentation","dataset":"Mapillary val","model":"Axial-DeepLab-L (multi-scale)","rank_in_archive_order":6,"of":13,"metrics":{"PQ":"41.1","PQst":"51.3","PQth":"33.4","mIoU":"58.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.07853","atlas_url":"https://app.syntology.ai/?focus=2003.07853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07853"}},"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/google-research/deeplab2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/The-AI-Summer/self_attention","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MartinGer/Stand-Alone-Axial-Attention","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/csrhddlam/axial-deeplab","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaofeng94/gmflownet","reach":null}],"summary":{"ran_draft_wrong":3,"ran":5,"unverified":3},"by_repo_kind":{"named_in_paper":{"samples":10,"ran":8,"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":"e4df01238c9e5ba5","entry":"cross_entropy_for_onehot","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/utils.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4df01238c9e5ba5"}},{"code_sha256_prefix":"9d1a2a8f3cd2f263","entry":"adjust_learning_rate","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/utils.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9d1a2a8f3cd2f263"}},{"code_sha256_prefix":"57c57f81551ed227","entry":"build_optimizer","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/build_optimizer.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/build_optimizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57c57f81551ed227"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/models/axialnet.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/models/axialnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/models/resnet.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"d951f27a92264740","entry":"imagenet1k","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/datasets/imagenet1k.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/datasets/imagenet1k.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d951f27a92264740"}},{"code_sha256_prefix":"5c9e8b037a72dcd8","entry":"label_smoothing","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/utils.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c9e8b037a72dcd8"}},{"code_sha256_prefix":"72e76034eb3a8502","entry":"resnet18","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/models/resnet.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72e76034eb3a8502"}},{"code_sha256_prefix":"67a7daffbe6a2857","entry":"axial26s","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/models/axialnet.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/models/axialnet.py","link_basis":"harvester_set","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":"67a7daffbe6a2857"}},{"code_sha256_prefix":"33a7ebf42fab13a5","entry":"axial50s","repo":"csrhddlam/axial-deeplab","repo_kind":"named_in_paper","path":"lib/models/axialnet.py","file_url":"https://github.com/csrhddlam/axial-deeplab/blob/HEAD/lib/models/axialnet.py","link_basis":"harvester_set","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":"33a7ebf42fab13a5"}},{"code_sha256_prefix":"10b86d2ef7ff73c5","entry":"prepare_data","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"10b86d2ef7ff73c5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}