DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

TLDR: DAformer as mentioned in this paper proposes a Transformer encoder and a multi-level context-aware feature fusion decoder for unsupervised domain adaptation (UDA), which is enabled by three crucial training strategies to stabilize the training and avoid overfitting.

Abstract: As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapted to real images without requiring their annotations. This process is studied in unsupervised domain adaptation (UDA). Even though a large number of methods propose new adaptation strategies, they are mostly based on outdated network architectures. As the influence of recent network architectures has not been systematically studied, we first benchmark different network architectures for UDA and then propose a novel UDA method, DAFormer, based on the benchmark results. The DAFormer network consists of a Transformer encoder and a multi-level context-aware feature fusion decoder. It is enabled by three simple but crucial training strategies to stabilize the training and to avoid overfitting DAFormer to the source domain: While the Rare Class Sampling on the source domain improves the quality of pseudo-labels by mitigating the confirmation bias of self-training towards common classes, the Thing-Class ImageNet Feature Distance and a learning rate warmup promote feature transfer from ImageNet pretraining. DAFormer significantly improves the state-of-the-art performance by 10.8 mIoU for GTA->Cityscapes and 5.4 mIoU for Synthia->Cityscapes and enables learning even difficult classes such as train, bus, and truck well. The implementation is available at https://github.com/lhoyer/DAFormer.