Paper
22 February 2023 Reference aware attention based medical image diagnosis
Qidan Dai, Wenhui Shen, Pike Xu, Heng Xiao, Xiao Qin
Author Affiliations +
Proceedings Volume 12587, Third International Seminar on Artificial Intelligence, Networking, and Information Technology (AINIT 2022); 1258719 (2023) https://doi.org/10.1117/12.2667605
Event: Third International Seminar on Artificial Intelligence, Networking, and Information Technology (AINIT 2022), 2022, Shanghai, China
Abstract
Given the excellent globality and parallelism, Transformer has been widely applied to image tasks. Visual Transformers demand modeling the spatial correlations among visual tokens. However, those existing methods either only emphasize the relative position between two tokens, or only concern on their contexts. Intuitively, a rational attention distribution should hinge on both. To this end, this paper proposes Reference Aware Attention (RAA). RAA decomposes inner-tokens dependency into three intuitive factors, in which reference bias is introduced to model how a reference token attends to a region. Experimental results suggest that RAA can effectively promote the performances of visual Transformers on various medical image diagnosis tasks.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Qidan Dai, Wenhui Shen, Pike Xu, Heng Xiao, and Xiao Qin "Reference aware attention based medical image diagnosis", Proc. SPIE 12587, Third International Seminar on Artificial Intelligence, Networking, and Information Technology (AINIT 2022), 1258719 (22 February 2023); https://doi.org/10.1117/12.2667605
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Transformers

Visualization

Medical imaging

Back to Top