Adopting multiple vision transformer layers for fine-grained image representation

• Main Authors: Sun, Fayou, Ngo, Hea Choon, Yu, Yelan, Xiao, Zhengyu, Meng, Zuqiang
• 格式: Conference or Workshop Item
• 语言: English
• 出版: 2023
• 在线阅读: http://eprints.utem.edu.my/id/eprint/27940/1/Adopting%20multiple%20vision%20transformer%20layers%20for%20fine-grained%20image%20representation.pdf; http://eprints.utem.edu.my/id/eprint/27940/; https://www-scopus-com.uitm.idm.oclc.org/record/display.uri?eid=2-s2.0-85174249067&origin=resultslist&sort=plf-f&src=s&sid=b55ff89e31efefd098739d17ce669a37&sot=

Accurate discriminative regions proposal has an important effect for fine-grained image recognition. The vision transformer (ViT) brings about a striking effect in computer vision duo to its innate muti-head self-attention mechanism. However, the attention maps are gradually similar after certain la...