Unsupervised Domain Adaptation with Implicit Pseudo Supervision for Semantic Segmentation

TL;DR

This paper introduces a tri-learning framework for unsupervised domain adaptation in semantic segmentation, leveraging implicit pseudo supervision and feature alignment to improve performance on domain shift tasks.

Contribution

It proposes a novel tri-learning architecture that uses implicit pseudo labels and distribution similarity for better domain adaptation in semantic segmentation.

Findings

Significant improvements on GTA5 to Cityscapes adaptation

Effective pseudo label alignment based on distribution similarity

Enhanced feature discrimination through triplet loss

Abstract

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and training process. In this paper, we train the model by the pseudo labels which are implicitly produced by itself to learn new complementary knowledge about target domain. Specifically, we propose a tri-learning architecture, where every two branches produce the pseudo labels to train the third one. And we align the pseudo labels based on the similarity of the probability distributions for each two branches. To further implicitly utilize the pseudo labels, we maximize the distances of features for different classes and minimize the distances for the same classes by triplet loss. Extensive experiments on GTA5 to Cityscapes and SYNTHIA to Cityscapes tasks show that the proposed method has considerable improvements.