CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation.
Yuqi LinMinghao ChenWenxiao WangBoxi WuKe LiBinbin LinHaifeng LiuXiaofei HePublished in: CoRR (2022)
Keyphrases
- weakly supervised
- semantic segmentation
- superpixels
- object class
- relation extraction
- topic models
- text mining
- named entities
- conditional random fields
- semi supervised
- natural images
- object categories
- multiscale
- object classes
- information retrieval
- object segmentation
- bounding box
- viewpoint
- image patches
- automatic extraction
- object detection