Feature Re-Representation and Reliable Pseudo Label Retraining for Cross-Domain Semantic Segmentation

Jing Li, Kang Zhou, Shenhan Qian, Wen Li, Lixin Duan, Shenghua Gao

Abstract:

This paper presents a novel unsupervised domain adaptation method for semantic segmentation. We argue that a good
representation of the target-domain data should keep both the knowledge from the source domain and the target-domain-specific
information. To obtain the knowledge from the source domain, we first learn a set of bases to characterize the feature distribution of the
source domain, then features from both the source and the target domain are re-represented as a weighted summation of the source
bases. A discriminator is additionally introduced to make the re-representation responsibilities of both domain features under the same
bases indistinguishable. In this way, the domain gap between the source re-representation and target re-representation is minimized,
and the re-represented target domain features contain the source domain information. Then we combine the feature re-representation
with the original domain-specific feature together for subsequent pixel-wise classification. To further make the re-represented target
features semantically meaningful, a Reliable Pseudo Label Retraining (RPLR) strategy is proposed, which utilizes the consistency of
the prediction by the networks trained with multi-view source images to select the clean pseudo labels on unlabeled target images for
re-training. Extensive experiments demonstrate the competitive performance of our approach for unsupervised domain adaptation on
the semantic segmentation benchmarks.