State of the art domain adaptation involves the creation of (1) a domain independent representation (DIRep) trained so that from that representation it is not possible to determine whether the input is from the source domain or the target and (2) a domain dependent representation (DDRep). The original input can then be reconstructed from those two representations. The classifier is trained only on source images using the DIRep. We show that information useful only in the source can be present in the DIRep, weakening the quality of the domain adaptation. To address this shortcoming, we ensure that DDRep is small and thus almost all information is available in the DIRep. We use synthetic data sets to illustrate a specific weakness, which we call the hidden data effect, and show in a simple context how our approach addresses it. We further showcase the performance of our approach against state-of-the-art algorithms using common image datasets. We also highlight the compatibility of our model with pretrained models, extending its applicability and versatility in real-world scenarios.

翻译：最先进的域适应涉及创建（1）域独立表示（DIRep），该表示经过训练使得无法从中判断输入来自源域还是目标域，以及（2）域依赖表示（DDRep）。原始输入可通过这两种表示重建。分类器仅使用DIRep在源图像上训练。我们发现仅对源域有用的信息可能存在于DIRep中，从而削弱域适应质量。为解决这一缺陷，我们确保DDRep尽可能小，从而使几乎所有信息均可从DIRep获得。我们利用合成数据集揭示一个特定弱点（称为隐藏数据效应），并在简单情境中展示我们的方法如何解决该问题。我们还通过常用图像数据集展示我们的方法与最先进算法的性能对比。同时，我们强调本模型与预训练模型的兼容性，从而扩展其在实际场景中的适用性和多功能性。