Semantic correlation promoted shape-variant context for segmentation
Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus ineffective or inefficient to aggregate various context informa...
Saved in:
Main Authors: | Ding, Henghui, Jiang, Xudong, Shuai, Bing, Liu, Ai Qun, Wang, Gang |
---|---|
其他作者: | School of Electrical and Electronic Engineering |
格式: | Conference or Workshop Item |
語言: | English |
出版: |
2020
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/140371 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
Semantic segmentation with context encoding and multi-path decoding
由: Ding, Henghui, et al.
出版: (2022) -
Boundary-aware feature propagation for scene segmentation
由: Ding, Henghui, et al.
出版: (2020) -
SpSequenceNet : semantic segmentation network on 4D point clouds
由: Shi, Hanyu, et al.
出版: (2020) -
Semantic segmentation of delayered IC images with shape-variant convolution
由: Wang, Xue
出版: (2022) -
Visual odometry in dynamic environments using light weight semantic segmentation
由: Tan Ai, Richard Josiah C., et al.
出版: (2019)