{"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/visual-attention-network","title":"Visual Attention Network","arxiv_id":"2202.09741","date":"2022-02-20","proceeding":null,"authors":["Meng-Hao Guo","Cheng-Ze Lu","Zheng-Ning Liu","Ming-Ming Cheng","Shi-Min Hu"],"abstract":"While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in computer vision. (1) Treating images as 1D sequences neglects their 2D structures. (2) The quadratic complexity is too expensive for high-resolution images. (3) It only captures spatial adaptability but ignores channel adaptability. In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings. Furthermore, we present a neural network based on LKA, namely Visual Attention Network (VAN). While extremely simple, VAN surpasses similar size vision transformers(ViTs) and convolutional neural networks(CNNs) in various tasks, including image classification, object detection, semantic segmentation, panoptic segmentation, pose estimation, etc. For example, VAN-B6 achieves 87.8% accuracy on ImageNet benchmark and set new state-of-the-art performance (58.2 PQ) for panoptic segmentation. Besides, VAN-B2 surpasses Swin-T 4% mIoU (50.1 vs. 46.1) for semantic segmentation on ADE20K benchmark, 2.6% AP (48.8 vs. 46.2) for object detection on COCO dataset. It provides a novel method and a simple yet strong baseline for the community. Code is available at https://github.com/Visual-Attention-Network.","url_abs":"https://arxiv.org/abs/2202.09741v5","url_pdf":"https://arxiv.org/pdf/2202.09741v5.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":"visual-attention-network","repo_url":"https://github.com/Visual-Attention-Network/VAN-Classification","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/open-mmlab/mmclassification","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/DarshanDeshpande/jax-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/EMalagoli92/VAN-Classification-TensorFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/Jittor-Image-Models/Jittor-Image-Models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/Visual-Attention-Network/VAN-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/chengtan9907/simvpv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/facebookresearch/xformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/lucasjinreal/yolov7_d2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/sithu31296/semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/Asthestarsfalll/VAN-MegEngine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/MenghaoGuo/Awesome-Vision-Attentions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/MindCode-4/code-1/tree/main/van","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"visual-attention-network","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"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/Visual-Attention-Network/VAN-Jittor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/flytocc/PaddleClas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/5/van","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"visual-attention-network","repo_url":"https://github.com/shkarupa-alex/tfvan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"visual-attention-network","repo_url":"https://gitlab.com/birder/birder","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":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B6 (22K, 384res)","rank_in_archive_order":70,"of":1060,"metrics":{"GFLOPs":"114.3","Number of params":"200M","Top 1 Accuracy":"87.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B5 (22K, 384res)","rank_in_archive_order":111,"of":1060,"metrics":{"GFLOPs":"50.6","Top 1 Accuracy":"87%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B6 (22K)","rank_in_archive_order":120,"of":1060,"metrics":{"GFLOPs":"38.9","Number of params":"200M","Top 1 Accuracy":"86.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B4 (22K, 384res)","rank_in_archive_order":133,"of":1060,"metrics":{"GFLOPs":"35.9","Number of params":"60M","Top 1 Accuracy":"86.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B5 (22K)","rank_in_archive_order":159,"of":1060,"metrics":{"GFLOPs":"17.2","Number of params":"90M","Top 1 Accuracy":"86.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B4 (22K)","rank_in_archive_order":204,"of":1060,"metrics":{"GFLOPs":"12.2","Top 1 Accuracy":"85.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B2","rank_in_archive_order":497,"of":1060,"metrics":{"GFLOPs":"5","Number of params":"26.6M","Top 1 Accuracy":"82.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B1","rank_in_archive_order":664,"of":1060,"metrics":{"GFLOPs":"2.5","Number of params":"13.9M","Top 1 Accuracy":"81.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VAN-B0","rank_in_archive_order":949,"of":1060,"metrics":{"GFLOPs":"0.9","Number of params":"4.1M","Top 1 Accuracy":"75.4%"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-minival","task":"Panoptic Segmentation","dataset":"COCO minival","model":"Visual Attention Network (VAN-B6 + Mask2Former)","rank_in_archive_order":10,"of":31,"metrics":{"PQ":"58.2","PQst":"48.2","PQth":"64.8"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-panoptic","task":"Panoptic Segmentation","dataset":"COCO panoptic","model":"VAN-B6*","rank_in_archive_order":1,"of":2,"metrics":{"PQ":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"VAN-B6","rank_in_archive_order":58,"of":235,"metrics":{"Validation mIoU":"54.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"VAN-Large (HamNet)","rank_in_archive_order":117,"of":235,"metrics":{"Params (M)":"55","Validation mIoU":"50.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"VAN-Large","rank_in_archive_order":151,"of":235,"metrics":{"Params (M)":"49","Validation mIoU":"48.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"VAN-Base (Semantic-FPN)","rank_in_archive_order":173,"of":235,"metrics":{"Validation mIoU":"46.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"VAN-Small","rank_in_archive_order":213,"of":235,"metrics":{"Params (M)":"18","Validation mIoU":"42.9"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"VAN-Tiny","rank_in_archive_order":221,"of":235,"metrics":{"Params (M)":"8","Validation mIoU":"38.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2202.09741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09741"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Westlake-AI/openmixup","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Visual-Attention-Network/VAN-Segmentation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"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/Visual-Attention-Network/VAN-Jittor","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucasjinreal/yolov7_d2","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Visual-Attention-Network/VAN-Classification","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/5/van","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmclassification","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EMalagoli92/VAN-Classification-TensorFlow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shkarupa-alex/tfvan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/birder/birder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flytocc/PaddleClas","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DarshanDeshpande/jax-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chengtan9907/simvpv2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MenghaoGuo/Awesome-Vision-Attentions","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sithu31296/semantic-segmentation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Jittor-Image-Models/Jittor-Image-Models","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Asthestarsfalll/VAN-MegEngine","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/xformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-1/tree/main/van","reach":null}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":5,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"365afdb1239780d8","entry":"convert_name","repo":"shkarupa-alex/tfvan","repo_kind":"listed","path":"convert_weights.py","file_url":"https://github.com/shkarupa-alex/tfvan/blob/HEAD/convert_weights.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":"365afdb1239780d8"}},{"code_sha256_prefix":"250a0be2cff73866","entry":"convert_weight","repo":"shkarupa-alex/tfvan","repo_kind":"listed","path":"convert_weights.py","file_url":"https://github.com/shkarupa-alex/tfvan/blob/HEAD/convert_weights.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":"250a0be2cff73866"}},{"code_sha256_prefix":"07d3401919c8d206","entry":"load_model_weights","repo":"Visual-Attention-Network/VAN-Classification","repo_kind":"official","path":"models/van.py","file_url":"https://github.com/Visual-Attention-Network/VAN-Classification/blob/HEAD/models/van.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":"07d3401919c8d206"}},{"code_sha256_prefix":"1e7a21b70e475e05","entry":"norm_cdf","repo":"EMalagoli92/VAN-Classification-TensorFlow","repo_kind":"listed","path":"van_classification_tensorflow/models/layers/utils.py","file_url":"https://github.com/EMalagoli92/VAN-Classification-TensorFlow/blob/HEAD/van_classification_tensorflow/models/layers/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":"1e7a21b70e475e05"}},{"code_sha256_prefix":"5e6f2f4822f14d6f","entry":"preprocess_input","repo":"shkarupa-alex/tfvan","repo_kind":"listed","path":"tfvan/prep.py","file_url":"https://github.com/shkarupa-alex/tfvan/blob/HEAD/tfvan/prep.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":"5e6f2f4822f14d6f"}},{"code_sha256_prefix":"6fc63671bfbb6c99","entry":"trunc_normal_","repo":"EMalagoli92/VAN-Classification-TensorFlow","repo_kind":"listed","path":"van_classification_tensorflow/models/layers/utils.py","file_url":"https://github.com/EMalagoli92/VAN-Classification-TensorFlow/blob/HEAD/van_classification_tensorflow/models/layers/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":"6fc63671bfbb6c99"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}