SegViT: Semantic Segmentation with Plain Vision Transformers.
Bowen ZhangZhi TianQuan TangXiangxiang ChuXiaolin WeiChunhua ShenYifan LiuPublished in: NeurIPS (2022)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- conditional random fields
- label transfer
- vision system
- weakly supervised
- scene classification
- computer vision
- object categories
- object class
- image processing
- segmentation algorithm
- object classes
- pascal voc
- image understanding
- pairwise
- object detection
- image representation
- input image
- generative model
- natural images
- multiscale