Adversarial learning baselines for domain adaptation (DA) approaches in the context of semantic segmentation are under explored in semi-supervised framework. These baselines involve solely the available labeled target samples in the supervision loss. In this work, we propose to enhance their usefulness on both semantic segmentation and the single domain classifier neural networks. We design new training objective losses for cases when labeled target data behave as source samples or as real target samples. The underlying rationale is that considering the set of labeled target samples as part of source domain helps reducing the domain discrepancy and, hence, improves the contribution of the adversarial loss. To support our approach, we consider a complementary method that mixes source and labeled target data, then applies the same adaptation process. We further propose an unsupervised selection procedure using entropy to optimize the choice of labeled target samples for adaptation. We illustrate our findings through extensive experiments on the benchmarks GTA5, SYNTHIA, and Cityscapes. The empirical evaluation highlights competitive performance of our proposed approach.

翻译：在语义分割的域适应方法中，对抗性学习基线在半监督框架下尚未得到充分探索。这些基线仅将可用的标记目标样本纳入监督损失中。本研究旨在提升其在语义分割和单域分类器神经网络中的实用性。我们针对标记目标数据作为源样本或真实目标样本的两种情况，设计了新的训练目标损失函数。其核心理念是：将标记目标样本集视为源域的一部分有助于减少域差异，从而增强对抗性损失的贡献。为支持该方法，我们提出了一种互补策略，将源数据与标记目标数据混合，并应用相同的适应过程。进一步地，我们提出了一种基于熵的无监督选择流程，以优化用于适应的标记目标样本选择。通过在GTA5、SYNTHIA和Cityscapes基准上的大量实验验证，实证评估表明我们的方法具有竞争力的性能。