DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation.
Zilu GuoLiuyang BianXuan HuangHu WeiJingyu LiHuasheng NiPublished in: CoRR (2024)
Keyphrases
- semantic segmentation
- street scenes
- conditional random fields
- scene classification
- superpixels
- label transfer
- object categories
- object class
- weakly supervised
- object classes
- object recognition
- object detection
- pascal voc
- graphical models
- multiple images
- long range
- image understanding
- named entities
- object classification
- generative model
- co occurrence
- bayesian networks