Loop and distillation: Attention weights fusion transformer for fine‐grained representation

Abstract Learning subtle discriminative feature representation plays a significant role in Fine‐Grained Visual Categorisation (FGVC). The vision transformer (ViT) achieves promising performance in the traditional image classification filed due to its multi‐head self‐attention mechanism. Unfortunatel...

Full description

Bibliographic Details

Published in:	IET Computer Vision
Main Authors:	Sun Fayou, Hea Choon Ngo, Zuqiang Meng, Yong Wee Sek
Format:	Article
Language:	English
Published:	Wiley 2023-06-01
Subjects:	computer vision fine‐grained image recognition image processing
Online Access:	https://doi.org/10.1049/cvi2.12181