Self-regulation for semantic segmentation
In this paper, we seek reasons for the two major failure cases in Semantic Segmentation (SS): 1) missing small objects or minor object parts, and 2) mislabeling minor parts of large objects as wrong classes. We have an interesting finding that Failure-1 is due to the underuse of detailed features an...
Saved in:
Main Authors: | ZHANG, Dong, ZHANG, Hanwang, TANG, Jinhui, HUA, Xian-Sheng, SUN, Qianru |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6230 https://ink.library.smu.edu.sg/context/sis_research/article/7233/viewcontent/Zhang_Self_Regulation_for_Semantic_Segmentation_ICCV_2021_paper.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Semantic scene completion with cleaner self
by: WANG, Fengyun, et al.
Published: (2023) -
Transporting causal mechanisms for unsupervised domain adaptation
by: YUE, Zhongqi, et al.
Published: (2021) -
Class re-activation maps for weakly-supervised semantic segmentation
by: CHEN, Zhaozheng, et al.
Published: (2022) -
Transferring and regularizing prediction for semantic segmentation
by: ZHANG, Yiheng, et al.
Published: (2020) -
Causal attention for unbiased visual recognition
by: WANG, Tan, et al.
Published: (2021)