Source-Free Open Compound Domain Adaptation in Semantic Segmentation

• Published in: IEEE transactions on circuits and systems for video technology 2022-10, Vol.32 (10), p.7019-7032
• Main Authors: Zhao, Yuyang, Zhong, Zhun, Luo, Zhiming, Lee, Gim Hee, Sebe, Nicu
• Format: Article
• Language: English
• Subjects: Adaptation; Adaptation models; Compounds; Data models; Data storage; Domains; Image segmentation; Labels; open compound domain adaptation; Semantic segmentation; Semantics; source-free domain adaptation; Supervised learning; Training; Transfer learning
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2022.3179021

In this work, we introduce a new concept, named source-free open compound domain adaptation (SF-OCDA), and study it in semantic segmentation. SF-OCDA is more challenging than the traditional domain adaptation but it is more practical. It jointly considers (1) the issues of data privacy and data storage and (2) the scenario of multiple target domains and unseen open domains. In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model. The model is evaluated on the samples from the target and unseen open domains. To solve this problem, we present an effective framework by separating the training process into two stages: (1) pre-training a generalized source model and (2) adapting a target model with self-supervised learning. In our framework, we propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level, which can benefit the training of both stages. First, CPSS can significantly improve the generalization ability of the source model, providing more accurate pseudo-labels for the latter stage. Second, CPSS can reduce the influence of noisy pseudo-labels and also avoid the model overfitting to the target domain during self-supervised learning, consistently boosting the performance on the target and open domains. Experiments demonstrate that our method produces state-of-the-art results on the C-Driving dataset. Furthermore, our model also achieves the leading performance on CityScapes for domain generalization.