{"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/neighborhood-attention-transformer","title":"Neighborhood Attention Transformer","arxiv_id":"2204.07143","date":"2022-04-14","proceeding":"CVPR 2023 1","authors":["Ali Hassani","Steven Walton","Jiachen Li","Shen Li","Humphrey Shi"],"abstract":"We present Neighborhood Attention (NA), the first efficient and scalable sliding-window attention mechanism for vision. NA is a pixel-wise operation, localizing self attention (SA) to the nearest neighboring pixels, and therefore enjoys a linear time and space complexity compared to the quadratic complexity of SA. The sliding-window pattern allows NA's receptive field to grow without needing extra pixel shifts, and preserves translational equivariance, unlike Swin Transformer's Window Self Attention (WSA). We develop NATTEN (Neighborhood Attention Extension), a Python package with efficient C++ and CUDA kernels, which allows NA to run up to 40% faster than Swin's WSA while using up to 25% less memory. We further present Neighborhood Attention Transformer (NAT), a new hierarchical transformer design based on NA that boosts image classification and downstream vision performance. Experimental results on NAT are competitive; NAT-Tiny reaches 83.2% top-1 accuracy on ImageNet, 51.4% mAP on MS-COCO and 48.4% mIoU on ADE20K, which is 1.9% ImageNet accuracy, 1.0% COCO mAP, and 2.6% ADE20K mIoU improvement over a Swin model with similar size. To support more research based on sliding-window attention, we open source our project and release our checkpoints at: https://github.com/SHI-Labs/Neighborhood-Attention-Transformer .","url_abs":"https://arxiv.org/abs/2204.07143v5","url_pdf":"https://arxiv.org/pdf/2204.07143v5.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":"neighborhood-attention-transformer","repo_url":"https://github.com/SHI-Labs/Neighborhood-Attention-Transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neighborhood-attention-transformer","repo_url":"https://github.com/shi-labs/natten","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neighborhood-attention-transformer","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neighborhood-attention-transformer","repo_url":"https://github.com/qwopqwop200/Neighborhood-Attention-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neighborhood-attention-transformer","repo_url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/nat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"na","method_name":"Neighborhood Attention"}],"datasets_introduced":[],"methods_introduced":[{"slug":"na","name":"Neighborhood Attention","full_name":"Neighborhood Attention"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NAT-Base","rank_in_archive_order":331,"of":1060,"metrics":{"GFLOPs":"13.7","Number of params":"90M","Top 1 Accuracy":"84.3%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NAT-Small","rank_in_archive_order":397,"of":1060,"metrics":{"GFLOPs":"7.8","Number of params":"51M","Top 1 Accuracy":"83.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NAT-Tiny","rank_in_archive_order":454,"of":1060,"metrics":{"GFLOPs":"4.3","Number of params":"28M","Top 1 Accuracy":"83.2%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"NAT-Mini","rank_in_archive_order":608,"of":1060,"metrics":{"GFLOPs":"2.7","Number of params":"20M","Top 1 Accuracy":"81.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"NAT-Base","rank_in_archive_order":126,"of":235,"metrics":{"GFLOPs (512 x 512)":"1137","Params (M)":"123","Validation mIoU":"49.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"NAT-Small","rank_in_archive_order":131,"of":235,"metrics":{"GFLOPs (512 x 512)":"1010","Params (M)":"82","Validation mIoU":"49.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"NAT-Tiny","rank_in_archive_order":145,"of":235,"metrics":{"GFLOPs (512 x 512)":"934","Params (M)":"58","Validation mIoU":"48.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"NAT-Mini","rank_in_archive_order":176,"of":235,"metrics":{"GFLOPs (512 x 512)":"900","Params (M)":"50","Validation mIoU":"46.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.07143","atlas_url":"https://app.syntology.ai/?focus=2204.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.07143"}},"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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shi-labs/natten","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SHI-Labs/Neighborhood-Attention-Transformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/nat","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qwopqwop200/Neighborhood-Attention-Transformer","reach":null}],"summary":{"ran_violates":1},"by_repo_kind":{"listed":{"samples":1,"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":"c5acf386fe00c470","entry":"GET_BLOCKS","repo":"qwopqwop200/Neighborhood-Attention-Transformer","repo_kind":"listed","path":"NAT_cuda.py","file_url":"https://github.com/qwopqwop200/Neighborhood-Attention-Transformer/blob/HEAD/NAT_cuda.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5acf386fe00c470"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}