{"url":"/method/sanet","slug":"sanet","name":"SANet","full_name":"Self-Attention Network","full_name_withheld":false,"description_markdown":"**Self-Attention Network** (**SANet**) proposes two variations of self-attention used for image recognition: 1) pairwise self-attention which generalizes standard [dot-product attention](https://paperswithcode.com/method/dot-product-attention) and is fundamentally a set operator, and 2) patchwise self-attention which is strictly more powerful than [convolution](https://paperswithcode.com/method/convolution).","description_state":"present","introduced_year":null,"introduced_by":{"title":"Exploring Self-attention for Image Recognition","paper":"/paper/exploring-self-attention-for-image","first_author":"Hengshuang Zhao","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/exploring-self-attention-for-image"},"source":{"url":"https://arxiv.org/abs/2004.13621v1","title":"Exploring Self-attention for Image Recognition","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Models","url":"/methods/category/image-models","pwc_aliases":[]}],"n_papers_tagged":11,"archive_num_papers":11,"papers_newest_first":[{"paper":"/paper/counting-manatee-aggregations-using-deep","title":"Counting Manatee Aggregations using Deep Neural Networks and Anisotropic Gaussian Kernel","date":"2023-11-04","arxiv_id":"2311.02315","n_code_links":1,"syntology":null},{"paper":"/paper/spatial-assistant-encoder-decoder-network-for","title":"Spatial-Assistant Encoder-Decoder Network for Real Time Semantic Segmentation","date":"2023-09-19","arxiv_id":"2309.10519","n_code_links":1,"syntology":null},{"paper":"/paper/strip-attention-for-image-restoration","title":"Strip Attention for Image Restoration","date":"2023-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/structure-aggregation-for-cross-spectral","title":"Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Artistic Arbitrary Style Transfer","date":"2022-12-21","arxiv_id":"2212.11376","n_code_links":0,"syntology":null},{"paper":null,"title":"Playing Lottery Tickets in Style Transfer Models","date":"2022-03-25","arxiv_id":"2203.13802","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-separable-attention-for-multi","title":"Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution","date":"2021-09-03","arxiv_id":"2109.01664","n_code_links":1,"syntology":null},{"paper":"/paper/shallow-attention-network-for-polyp","title":"Shallow Attention Network for Polyp Segmentation","date":"2021-08-02","arxiv_id":"2108.00882","n_code_links":1,"syntology":null},{"paper":"/paper/learning-camera-localization-via-dense-scene","title":"Learning Camera Localization via Dense Scene Matching","date":"2021-03-31","arxiv_id":"2103.16792","n_code_links":1,"syntology":null},{"paper":null,"title":"Scale-aware Neural Network for Semantic Segmentation of Multi-resolution Remote Sensing Images","date":"2021-03-14","arxiv_id":"2103.07935","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-self-attention-for-image","title":"Exploring Self-attention for Image Recognition","date":"2020-04-28","arxiv_id":"2004.13621","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":1}}],"papers_shown":11,"tasks":[{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/style-transfer","name":"Style Transfer","papers":2},{"task":"/task/super-resolution","name":"Super-Resolution","papers":2},{"task":"/task/camera-localization","name":"Camera Localization","papers":1},{"task":"/task/crowd-counting","name":"Crowd Counting","papers":1},{"task":"/task/deblurring","name":"Deblurring","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/image-dehazing","name":"Image Dehazing","papers":1},{"task":"/task/image-restoration","name":"Image Restoration","papers":1},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":1},{"task":"/task/real-time-semantic-segmentation","name":"Real-Time Semantic Segmentation","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/scene-recognition","name":"Scene Recognition","papers":1},{"task":"/task/scene-understanding","name":"Scene Understanding","papers":1},{"task":"/task/scheduling","name":"Scheduling","papers":1},{"task":"/task/self-driving-cars","name":"Self-Driving Cars","papers":1},{"task":"/task/stereo-matching-1","name":"Stereo Matching","papers":1}],"tasks_shown":20,"n_tasks":21,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":4},{"year":"2022","papers":2},{"year":"2023","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sanet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}