Research on Unsupervised Domain Adaptation to Reduce Labelling Costs

在WACV 2023期间，我们引入了基于分类器的特征空间的反向传播诱导加权。这种方法有两个主要优点。首先，它让领域分类器专注于对分类重要的特征，其次，它将分类和对抗分支更紧密地结合在一起。此外，我们还介绍了一种迭代标签分布对齐方法，该方法利用以前运行的结果来近似类平衡的数据加载器。我们目前正在完成一篇基于通过增量域扩展进行域自适应的论文，该论文逐渐采用越来越多的目标域特定特征。另外两篇与其他研究人员合作的论文已被ICPR 2022接受。

During WACV 2023, we introduced a classifier-based backprop-induced weighting of the feature space. This approach has two main advantages. Firstly, it lets the domain classifier focus on features that are important for the classification, and, secondly, it couples the classification and adversarial branch more closely. Furthermore, we introduce an iterative label distribution alignment method, that employs results of previous runs to approximate a class-balanced dataloader.We also are currently finalizing a paper based on domain adaptation via incremental domain enlargement, that incrementally employs more and more target domain specific features.Further two papers in collaboration with other researchers have been accepted for ICPR 2022.