Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer.
Zhihe LuSen HeXiatian ZhuLi ZhangYi-Zhe SongTao XiangPublished in: ICCV (2021)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- conditional random fields
- label transfer
- training data
- weakly supervised
- support vector
- object categories
- pascal voc
- feature selection
- decision trees
- scene classification
- training examples
- training set
- video data
- object classes
- object class
- video sequences
- bag of words
- image set
- support vector machine
- feature space
- training samples
- key frames
- image understanding
- computer vision
- object segmentation
- labeled data
- graph cuts
- pairwise
- object recognition