arrow
返回

Adversarial Dense Contrastive Learning for Semi-Supervised Semantic Segmentation

delete2023-01-01
delete3
PRE
AI
Y
Ying Wang *
Z
Ziwei Xuan
C
Chiuman Ho
G
Guo-Jun Qi
DOI:10.1109/TIP.2023.3299196delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Semi-supervised dense prediction tasks, such as semantic segmentation, can be greatly improved through the use of contrastive learning. However, this approach presents two key challenges: selecting informative negative samples from a highly redundant pool and implementing effective data augmentation. To address these challenges, we present an adversarial contrastive learning method specifically for semi-supervised semantic segmentation. Direct learning of adversarial negatives is adopted to retain discriminative information from the past, leading to higher learning efficiency. Our approach also leverages an advanced data augmentation strategy called AdverseMix, which combines information from under-performing classes to generate more diverse and challenging samples. Additionally, we use auxiliary labels and classifiers to prevent over-adversarial negatives from affecting the learning process. Our experiments on the Pascal VOC and Cityscapes datasets demonstrate that our method outperforms the state-of-the-art by a significant margin, even when using a small fraction of labeled data.
Keyword:
Semi-supervised learning
semantic segmentation
adversarial contrastive learning
data augmentation

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

T
Texas A&M University System
学者数:
4.4W
论文数: 4.0W
被引数: 4.0K
引用论文

引用论文

Capsular serotype ofStaphylococcus aureusin the era of community-acquired MRSA
err2011-10-01
err0
errOAAI
errDeena E. Sutter; Amy M. Summers; Christine E. Keys; Kimberly L. Taylor; Carl E. Frasch; LoRanee E. Braun; Ali I. Fattom; Margaret C. Bash
err分享
err收藏
err分享
err收藏
Stability of adaptive behaviors in middle-school children with autism spectrum disorders
err2007-10-01
err0
PREAI
errRobin L. Gabriels; Bonnie Jean Ivers; Dina E. Hill; John A. Agnew; John McNeill
err分享
err收藏
学者 查看更多内容