IDPL：基于动态伪标签的子域内自适应对抗学习分割方法
IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels
摘要：
将无监督领域自适应（UDA）方法应用于图像语义分割，以解决域偏移问题。但在一些识别精度不高的疑难类别中，分割效果仍不理想。为此，本文提出了一种基于动态伪标签（IDPL）的子域内自适应对抗学习分割方法。整个过程包括3个步骤：首先，提出了实例级伪标签动态生成模块，融合全局类和局部实例中的类匹配信息，自适应地为每个类生成最优阈值，得到高质量的伪标签。其次，构建了基于实例置信度的子域分类器模块，该模块能够根据易、难实例的相对比例，动态地将目标域划分为易、难子域。最后，提出了基于自注意的子域对抗学习模型。该方法利用多头自注意力，在类级上对易、难两类子领域进行对抗，生成高质量的伪标签，集中挖掘目标领域图像高熵区域中难类的特征，促进子领域之间的类级条件分布对齐，提高难类的分割性能。实验结果表明，对于较难的类别，IDPL的性能与其他最新的主流方法相比有明显的提高。
英文摘要：
Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal. To this end, in this paper, Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels(IDPL) is proposed. The whole process consists of 3 steps: Firstly, the instance-level pseudo label dynamic generation module is proposed, which fuses the class matching information in global classes and local instances, thus adaptively generating the optimal threshold for each class, obtaining high-quality pseudo labels. Secondly, the subdomain classifier module based on instance confidence is constructed, which can dynamically divide the target domain into easy and difficult subdomains according to the relative proportion of easy and difficult instances. Finally, the subdomain adversarial learning module based on self-attention is proposed. It uses multi-head self-attention to confront the easy and difficult subdomains at the class level with the help of generated high-quality pseudo labels, so as to focus on mining the features of difficult categories in the high-entropy region of target domain images, which promotes class-level conditional distribution alignment between the subdomains, improving the segmentation performance of difficult categories. For the difficult categories, the experimental results show that the performance of IDPL is significantly improved compared with other latest mainstream methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
