Pseudolabel guided pixels contrast for domain adaptive semantic segmentation
Authors:
Open Access
- 30 December 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-18
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 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.Keywords
All Related Versions
This publication has 60 references indexed in Scilit:
- Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation2022
- HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation2022
- Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation2022
- Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation2022
- Instance Adaptive Self-training for Unsupervised Domain Adaptation2020
- Object-Contextual Representations for Semantic Segmentation2020
- Knowledge based domain adaptation for semantic segmentationKnowledge-Based Systems, 2020
- Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training2018
- Playing for Data: Ground Truth from Computer Games2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015