PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
CVPR 2024（2024）
Key words
Domain Generalization,Vision-language Models,Robust Algorithm,Open Set,Target Domain,Visual Model,SET Domain,Source Domain,Unseen Classes,Semantic,Computational Cost,Data Augmentation,Single Domain,Large Margin,Baseline Methods,Ground Truth Labels,Training Objective,Maximum Similarity,Identity Labels,Label Space,SOTA Methods,Image Encoder,Image Embedding,Vision Transformer,Text Encoder,Unseen Domains,Unknown Category
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined