Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation.
Yazhou YaoTao ChenGuo-Sen XieChuanyi ZhangFumin ShenQi WuZhenmin TangJian ZhangPublished in: CoRR (2021)
Keyphrases
- weakly supervised
- semantic segmentation
- superpixels
- object classes
- object class
- object segmentation
- object detectors
- relation extraction
- topic models
- semi supervised
- bounding box
- multiple objects
- object categories
- object model
- text mining
- named entities
- partial occlusion
- conditional random fields
- pixel level
- object detection
- d objects
- multiscale
- saliency map
- image set
- object tracking
- object recognition
- image segmentation
- image patches
- visual attention
- image regions
- generative model
- natural images
- graph cuts
- text classification
- moving objects