BAT: Bi-Alignment Based on Transformation in Multi-Target Domain Adaptation for Semantic Segmentation

While single-target domain adaptive semantic segmentation (ST-DASS) has recently made great progress, the multi-target domain of the multi-peak distribution cannot be directly aligned well with the single-peak distributed source domain, making it impossible for existing methods to handle the more realistic multi-target domain adaptive semantic segmentation (MT-DASS) tasks. In this paper, we propose a Bi-Alignment framework based on Transformation (BAT). Specifically, we employ the Fourier style transform to convert the style of the source domain to that of the target domain without training any style transfer networks. In this way, we transform the single-peak distributed source domain into a multi-peak distribution that resembles the multi-target domain. Then, we perform fine-grained global and local dual distribution alignment between pairs of source-target domains with the same style to achieve a multi-to-multi distribution alignment. Finally, self-training is utilized to further improve the discriminability of the network. Experimental results show that our approach achieves competitive results over state-of-the-art methods.