@inproceedings{Hoyer_CVPR2022,
TITLE = {{DAFormer}: {I}mproving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation},
AUTHOR = {Hoyer, Lukas and Dai, Dengxin and Van Gool, Luc},
LANGUAGE = {eng},
ISBN = {978-1-6654-6946-3},
DOI = {10.1109/CVPR52688.2022.00969},
PUBLISHER = {IEEE},
YEAR = {2022},
ABSTRACT = {As acquiring pixel-wise annotations of real-world images for semantic<br>segmentation is a costly process, a model can instead be trained with more<br>accessible synthetic data and adapted to real images without requiring their<br>annotations. This process is studied in unsupervised domain adaptation (UDA).<br>Even though a large number of methods propose new adaptation strategies, they<br>are mostly based on outdated network architectures. As the influence of recent<br>network architectures has not been systematically studied, we first benchmark<br>different network architectures for UDA and then propose a novel UDA method,<br>DAFormer, based on the benchmark results. The DAFormer network consists of a<br>Transformer encoder and a multi-level context-aware feature fusion decoder. It<br>is enabled by three simple but crucial training strategies to stabilize the<br>training and to avoid overfitting DAFormer to the source domain: While the Rare<br>Class Sampling on the source domain improves the quality of pseudo-labels by<br>mitigating the confirmation bias of self-training towards common classes, the<br>Thing-Class ImageNet Feature Distance and a learning rate warmup promote<br>feature transfer from ImageNet pretraining. DAFormer significantly improves the<br>state-of-the-art performance by 10.8 mIoU for GTA->Cityscapes and 5.4 mIoU for<br>Synthia->Cityscapes and enables learning even difficult classes such as train,<br>bus, and truck well. The implementation is available at<br>https://github.com/lhoyer/DAFormer.<br>},
BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)},
PAGES = {9914--9925},
ADDRESS = {New Orleans, LA, USA},
}