Papers › Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic...
Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation
Robert A. Marsden, Alexander Bartler, Mario Döbler, Bin Yang
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 → Cityscapes and SYNTHIA → Cityscapes. Our method achieves better or comparable results than the state-of-the-art. We will make the code publicly available.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Synthetic-to-Real Translation | GTAV-to-Cityscapes Labels | CLST | mIoU | 51.6 | #41 of 73 | Archive leaderboard | report |
| Synthetic-to-Real Translation | SYNTHIA-to-Cityscapes | CLST(ResNet-101) | MIoU (13 classes) | 57.8 | #22 of 38 | Archive leaderboard | report |
| Synthetic-to-Real Translation | SYNTHIA-to-Cityscapes | CLST(ResNet-101) | MIoU (16 classes) | 49.8 | #22 of 38 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections