CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation
This addresses the problem of adapting semantic segmentation models across domains without labeled target data, offering an incremental improvement over existing methods.
The paper tackles unsupervised domain adaptation for semantic segmentation by proposing CLUDA, a method that integrates contrastive losses into a student-teacher paradigm using pseudo-labels, achieving state-of-the-art results with 74.4 mIOU on GTA→Cityscapes and 67.2 mIOU on Synthia→Cityscapes.
In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of pseudo-labels generated from the target domain by the teacher network. More specifically, we extract a multi-level fused-feature map from the encoder, and apply contrastive loss across different classes and different domains, via source-target mixing of images. We consistently improve performance on various feature encoder architectures and for different domain adaptation datasets in semantic segmentation. Furthermore, we introduce a learned-weighted contrastive loss to improve upon on a state-of-the-art multi-resolution training approach in UDA. We produce state-of-the-art results on GTA $\rightarrow$ Cityscapes (74.4 mIOU, +0.6) and Synthia $\rightarrow$ Cityscapes (67.2 mIOU, +1.4) datasets. CLUDA effectively demonstrates contrastive learning in UDA as a generic method, which can be easily integrated into any existing UDA for semantic segmentation tasks. Please refer to the supplementary material for the details on implementation.