文献类型：期刊文献

英文题名：Pseudolabel guided pixels contrast for domain adaptive semantic segmentation

作者：Xiang, Jianzi[1];Wan, Cailu[1];Cao, Zhu[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2024

卷号：14

期号：1

外文期刊名：SCIENTIFIC REPORTS

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001389342800030)】；

基金：This work was partially supported by the National Key Research and Development Program of China (2021YFB3301303), the National Natural Science Foundation of China (12105105, 62273149), the startup fund from East China University of Science and Technology under Grant JKH01241603 and the Programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017.

语种：英文

外文关键词：Semantic segmentation; Unsupervised domain adaptation; Contrastive learning

摘要：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 technique that uses virtual data with labels to train a model and adapts it to real data without labels. Some recent works use contrastive learning, which is a powerful method for self-supervised learning, to help with this technique. However, these works do not take into account the diversity of features within each class when using contrastive learning, which leads to errors in class prediction. We analyze the limitations of these works and propose a novel framework called Pseudo-label Guided Pixel Contrast (PGPC), which overcomes the disadvantages of previous methods. We also investigate how to use more information from target images without adding noise from pseudo-labels. We test our method on two standard UDA benchmarks and show that it outperforms existing methods. Specifically, we achieve relative improvements of 5.1% mIoU and 4.6% mIoU on the Grand Theft Auto V (GTA5) to Cityscapes and SYNTHIA to Cityscapes tasks based on DAFormer, respectively. Furthermore, our approach can enhance the performance of other UDA approaches without increasing model complexity.