{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T14:14:56Z","timestamp":1789049696517,"version":"build-2803163510"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all keys\/values, various methods have constrained the range of attention  within local regions, where each query only attends to keys\/values within a hand-crafted window. However, these hand-crafted window partition mechanisms are data-agnostic and ignore their input content, so it is likely that one query maybe attend to irrelevant keys\/values. To address this issue, we propose a Dynamic Group Attention (DG-Attention), which dynamically divides all queries into multiple groups and selects the most relevant keys\/values for each group.  Our DG-Attention can flexibly model more relevant dependencies without any spatial constraint that is used in hand-crafted window based attention. Built on the DG-Attention, we develop a general vision transformer backbone named Dynamic Group Transformer (DGT). Extensive experiments show that our models can outperform the state-of-the-art methods on multiple common vision tasks, including image classification, semantic segmentation, object detection, and instance segmentation.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/166","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"1187-1193","source":"Crossref","is-referenced-by-count":13,"title":["Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention"],"prefix":"10.24963","author":[{"given":"Kai","family":"Liu","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Deep Learning, Baidu Research, Beijing, China"},{"name":"National Engineering Laboratory for Deep Learning Technology and Application, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Deep Learning, Baidu Research, Beijing, China"},{"name":"National Engineering Laboratory for Deep Learning Technology and Application, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","theme":"Artificial Intelligence","location":"Vienna, Austria","acronym":"IJCAI-2022","number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2022,7,23]]},"end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:08:06Z","timestamp":1658142486000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/166"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/166","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}