Wave-ViT: Unifying wavelet and transformers for visual representation learning

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly employ down-sampling operations (e.g., average pooling) over ke...

全面介紹

Saved in:
書目詳細資料
Main Authors: YAO, Ting, PAN, Yingwei, LI, Yehao, NGO, Chong-wah, MEI, Tao
格式: text
語言:English
出版: Institutional Knowledge at Singapore Management University 2022
主題:
在線閱讀:https://ink.library.smu.edu.sg/sis_research/7508
https://ink.library.smu.edu.sg/context/sis_research/article/8511/viewcontent/2207.04978.pdf
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
機構: Singapore Management University
語言: English

相似書籍