Pseudolabel guided pixels contrast for domain adaptive semantic segmentation
Abstract Semantic segmentation is essential for comprehending images, but the process necessitates a substantial amount of detailed annotations at the pixel level. Acquiring such annotations can be costly in the real-world. Unsupervised domain adaptation (UDA) for semantic segmentation is a techniqu...
Saved in:
Main Authors: | Jianzi Xiang, Cailu Wan, Zhu Cao |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-12-01
|
Series: | Scientific Reports |
Subjects: | |
Online Access: | https://doi.org/10.1038/s41598-024-78404-4 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Unsupervised domain adaptation multi-level adversarial network for semantic segmentation based on multi-modal features
by: Zeyu WANG, et al.
Published: (2022-12-01) -
Person re-identification with intra-domain similarity grouping based on semantic fusion
by: Qiqi KOU, et al.
Published: (2022-07-01) -
Mix-layers semantic extraction and multi-scale aggregation transformer for semantic segmentation
by: Tianping Li, et al.
Published: (2024-11-01) -
Structure preserved ordinal unsupervised domain adaptation
by: Qing Tian, et al.
Published: (2024-11-01) -
Examination of the Form and Content of “Semantics”, with a Contrastive Criticism Approach to the Translation
by: Yusuf Nazari
Published: (2017-03-01)