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...
Main Authors: | Ding, Henghui, Jiang, Xudong, Shuai, Bing, Liu, Ai Qun, Wang, Gang |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Conference Paper |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/140371 |
Similar Items
Similar Items
-
Boundary-aware feature propagation for scene segmentation
by: Ding, Henghui, et al.
Published: (2020) -
Semantic segmentation with context encoding and multi-path decoding
by: Ding, Henghui, et al.
Published: (2022) -
SpSequenceNet : semantic segmentation network on 4D point clouds
by: Shi, Hanyu, et al.
Published: (2020) -
Semantic segmentation of delayered IC images with shape-variant convolution
by: Wang, Xue
Published: (2022) -
CAP : Context-aware Pruning for semantic segmentation
by: He, Wei, et al.
Published: (2021)