Noranart Vesdapunt*

HVCLIP: High-dimensional Vector in CLIP for Unsupervised Domain Adaptation

"Recent advancement in the large-scale image-text pre-training model (such as CLIP) has significantly improved unsupervised domain adaptation (UDA) by leveraging the pre-trained knowledge to bridge the source and target domain gap. However, Catastrophic forgetting still remains to be the main challe…