Generating unlabeled data has been recently shown to help address the few-shot hypothesis adaptation (FHA) problem, where we aim to train a classifier for the target domain with a few labeled target-domain data and a well-trained source-domain classifier (i.e., a source hypothesis), for the additional information of the highly-compatible unlabeled data. However, the generated data of the existing methods are extremely similar or even the same. The strong dependency among the generated data will lead the learning to fail. In this paper, we propose a diversity-enhancing generative network (DEG-Net) for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC). Specifically, DEG-Net will generate data via minimizing the HSIC value (i.e., maximizing the independence) among the semantic features of the generated data. By DEG-Net, the generated unlabeled data are more diverse and more effective for addressing the FHA problem. Experimental results show that the DEG-Net outperforms existing FHA baselines and further verifies that generating diverse data plays a vital role in addressing the FHA problem

翻译：生成无标签数据近期被证明有助于解决少样本假设适应（FHA）问题，该问题旨在利用少量带标签的目标域数据和训练良好的源域分类器（即源假设），结合高度兼容的无标签数据所提供额外信息，训练针对目标域的分类器。然而，现有方法生成的数据极为相似甚至完全相同。生成数据之间的强依赖性将导致学习失败。本文针对FHA问题提出了一种多样性增强生成网络（DEG-Net），该网络借助核独立性度量——希尔伯特-施密特独立性准则（HSIC）生成多样化的无标签数据。具体而言，DEG-Net通过最小化生成数据语义特征之间的HSIC值（即最大化独立性）来生成数据。通过DEG-Net，生成的无标签数据更具多样性，从而更有效地解决FHA问题。实验结果表明，DEG-Net优于现有FHA基线方法，进一步证实生成多样化数据在解决FHA问题中发挥着关键作用。