Associating multiple vision transformer layers for fine-grained image representation

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

Full description

Bibliographic Details

Published in:	AI Open
Main Authors:	Fayou Sun, Hea Choon Ngo, Yong Wee Sek, Zuqiang Meng
Format:	Article
Language:	English
Published:	KeAi Communications Co. Ltd. 2023-01-01
Subjects:	Increasing vision transformer layers Weight attention fusion Feature detection enhancement
Online Access:	http://www.sciencedirect.com/science/article/pii/S2666651023000153