Multi-target domain adaptation (MTDA) for semantic segmentation poses a
significant challenge, as it involves multiple target domains with varying
distributions. The goal of MTDA is to minimize the domain discrepancies among a
single source and multi-target domains, aiming to train a single model that
excels across all target domains. Previous MTDA approaches typically employ
multiple teacher architectures, where each teacher specializes in one target
domain to simplify the task. However, these architectures hinder the student
model from fully assimilating comprehensive knowledge from all target-specific
teachers and escalate training costs with increasing target domains. In this
paper, we propose an ouroboric domain bridging (OurDB) framework, offering an
efficient solution to the MTDA problem using a single teacher architecture.
This framework dynamically cycles through multiple target domains, aligning
each domain individually to restrain the biased alignment problem, and utilizes
Fisher information to minimize the forgetting of knowledge from previous target
domains. We also propose a context-guided class-wise mixup (CGMix) that
leverages contextual information tailored to diverse target contexts in MTDA.
Experimental evaluations conducted on four urban driving datasets (i.e., GTA5,
Cityscapes, IDD, and Mapillary) demonstrate the superiority of our method over
existing state-of-the-art approaches.

多目标域自适应（MTDA）的研究挑战在于多个具有不同分布的目标域。本文提出了一种以单个教师架构为基础的 MTDA 框架，通过动态循环处理多个目标域，并利用 Fisher 信息来最小化对前面目标域知识的遗忘。同时，我们还提出了一种针对多目标域的上下文引导的类别混合技术（CGMix）。在四个城市驾驶数据集（GTA5、Cityscapes、IDD 和 Mapillary）上的实证评估表明，我们的方法优于现有的最先进方法。