{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:43Z","timestamp":1758672883572,"version":"3.44.0"},"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":[[2025,9]]},"abstract":"<jats:p>The hierarchical architecture has become a mainstream design paradigm for Vision Transformers (ViTs), with Patch Merging serving as the pivotal component that transforms a columnar architecture into a hierarchical one. Drawing inspiration from the brain's ability to integrate global and local information for comprehensive visual understanding, we propose Stepwise Patch Merging (SPM), which enhances the subsequent attention mechanism's ability to 'see' better. SPM consists of Multi-Scale Aggregation (MSA) and Guided Local Enhancement (GLE) striking a proper balance between long-range dependency modeling and local feature enhancement. Extensive experiments conducted on benchmark datasets, including ImageNet-1K, COCO, and ADE20K, demonstrate that SPM significantly improves the performance of various models, particularly in dense prediction tasks such as object detection and semantic segmentation. Meanwhile, experiments show that combining SPM with different backbones can further improve performance. The code has been released at https:\/\/github.com\/Yonghao-Yu\/StepwisePatchMerging.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/257","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"2305-2313","source":"Crossref","is-referenced-by-count":0,"title":["Brain-Inspired Stepwise Patch Merging for Vision Transformers"],"prefix":"10.24963","author":[{"given":"Yonghao","family":"Yu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"},{"name":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences"},{"name":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongcheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences"},{"name":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"},{"name":"Center for Long-term AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guobin","family":"Shen","sequence":"additional","affiliation":[{"name":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences"},{"name":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"},{"name":"School of Future Technology, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiting","family":"Dong","sequence":"additional","affiliation":[{"name":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences"},{"name":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"},{"name":"School of Future Technology, University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"},{"name":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences"},{"name":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"},{"name":"School of Future Technology, University of Chinese Academy of Sciences"},{"name":"Center for Long-term AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:33:29Z","timestamp":1758627209000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/257"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/257","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}