Markin-Wang/CLEViT
[IJCAI 2023] CLE-ViT: Contrastive Learning Encoded Transformer for Ultra-Fine-Grained Visual Categorization.
PythonMIT
Issues
- 3
Questions about code reproduction
#6 opened by 1084991943 - 1
我该如何训练自己的数据集?
#5 opened by Enuang - 2
How to visualize the attention heat map?
#4 opened by FriedaSmith - 8
Error loading pre-trained model
#1 opened by FriedaSmith - 1
正样本对构建问题
#3 opened by realfzyyyyy - 2
Where Paper?
#2 opened by CSer-Tang-hao