# Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation Source: [Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:31:20.156Z Authors: Robert A. Marsden, Alexander Bartler, Mario D\\"obler, Bin Yang Published: 2021-05-05T11:55:53.000Z ## Abstract Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different domain. To avoid the costly annotation of training data for unseen domains, unsupervised domain adaptation (UDA) attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain. Previous work has mainly focused on minimizing the discrepancy between the two domains by using adversarial training or self-training. While adversarial training may fail to align the correct semantic categories as it minimizes the discrepancy between the global distributions, self-training raises the question of how to provide reliable pseudo-labels. To align the correct semantic categories across domains, we propose a contrastive learning approach that adapts category-wise centroids across domains. Furthermore, we extend our method with self-training, where we use a memory-efficient temporal ensemble to generate consistent and reliable pseudo-labels. Although both contrastive learning and self-training (CLST) through temporal ensembling enable knowledge transfer between two domains, it is their combination that leads to a symbiotic structure. We validate our approach on two domain adaptation benchmarks: GTA5 $\\rightarrow$ Cityscapes and SYNTHIA $\\rightarrow$ Cityscapes. Our method achieves better or comparable results than the state-of-the-art. We will make the code publicly available. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Segmentation on SYNTHIA to Cityscapes (val)](): Semantic segmentation; SYNTHIA to Cityscapes (val); Rider IoU: 27.2. - [Semantic Segmentation on GTA5 → Cityscapes (val)](): Semantic segmentation; GTA5 → Cityscapes (val); mIoU: 51.6. ## Original sources and implementation [Original paper]() [PDF]()