Proceedings

Brain-Inspired Stepwise Patch Merging for Vision Transformers

Yonghao Yu, Dongcheng Zhao, Guobin Shen, Yiting Dong, Yi Zeng

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 2305-2313.

https://doi.org/10.24963/ijcai.2025/257

Keywords

  • Humans and AI: HAI: Cognitive modeling
  • Humans and AI: HAI: Cognitive systems
  • Computer Vision: CV: Recognition (object detection, categorization)
  • Computer Vision: CV: Representation learning

Abstract

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.

Yonghao Yu, Dongcheng Zhao, Guobin Shen, Yiting Dong, and Yi Zeng. 2025. Brain-Inspired Stepwise Patch Merging for Vision Transformers. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 2305–2313. https://doi.org/10.24963/ijcai.2025/257
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards