A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance.
Zeyi HuangAndy ZhouZijian LinMu CaiHaohan WangYong Jae LeePublished in: ICCV (2023)
Keyphrases
- image data
- image database
- natural language
- three dimensional
- ground truth
- image classification
- input image
- multiscale
- image matching
- image retrieval
- image registration
- image analysis
- multiple images
- image annotation
- region of interest
- object recognition
- image collections
- test images
- segmentation method
- text classification
- edge detection
- programming language
- feature points
- language learning
- rigid body
- syntactic parsing