Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs.
Junbum ChaJonghwan MunByungseok RohPublished in: CoRR (2022)
Keyphrases
- semantic segmentation
- weakly supervised
- image features
- text mining
- multiscale
- information retrieval
- input image
- learning algorithm
- database
- image segmentation
- single image
- active learning
- image content
- pixel level
- bayesian networks
- supervised learning
- image representation
- scene classification
- superpixels
- segmentation method
- image set
- image matching
- topic models
- object recognition