2 papers
cs.CV2025
One Last Attention for Your Vision-Language Model
Liang Chen, Ghazi Shazan Ahmad, Tianjun Yao +2
Pretrained vision-language models (VLMs), such as CLIP, achieve remarkable zero-shot performance, yet their downstream potential hinges on effective fine-tuning. Most adaptation me…
cs.LG2024
LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization
Liang Chen, Yong Zhang, Yibing Song +2
Domain generalization (DG) methods aim to maintain good performance in an unseen target domain by using training data from multiple source domains. While success on certain occasio…