I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation.
Haoyu MaXiangru LinYizhou YuPublished in: CoRR (2023)
Keyphrases
- semantic segmentation
- image features
- image data
- superpixels
- multiscale
- scene classification
- input image
- image classification
- conditional random fields
- image retrieval
- image segmentation
- weakly supervised
- image set
- segmentation method
- region of interest
- object categories
- high resolution
- pixel level
- single image
- image regions
- image matching
- test images
- viewpoint
- computer vision
- segmentation algorithm
- image database
- object classes
- object class
- feature vectors
- pascal voc