Runyi Yu, Zhennan Wang, Yinhuai Wang, Kehan Li 0002, Chang Liu, Haoyi Duan, Xiangyang Ji, Jie Chen 0001. LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. pages 5863-5873, IEEE, 2023. [doi]
Abstract is missing.