CLE-ViT: Contrastive Learning Encoded Transformer for Ultra-Fine-Grained Visual Categorization.

Xiaohan Yu Jun Wang Yongsheng Gao

Published in: IJCAI (2023)

Keyphrases

fine grained
visual recognition
coarse grained
learning algorithm
learning process
prior knowledge
visual categorization
access control
active learning
learning tasks
object recognition