Abstract
Many methods have been proposed to solve the domain adaptation problem recently. However, the success of them implicitly funds on the assumption that the information of domains are fully transferrable. If the assumption is not satisfied, the effect of negative transfer may degrade domain adaptation. In this paper, a better learning network has been proposed by considering three tasks - domain adaptation, disentangled representation, and style transfer simultaneously. Firstly, the learned features are disentangled into common parts and specific parts. The common parts represent the transferrable features, which are suitable for domain adaptation with less negative transfer. Conversely, the specific parts characterize the unique style of each individual domain. Based on this, the new concept of feature exchange across domains, which can not only enhance the transferability of common features but also be useful for image style transfer, is introduced. These designs allow us to introduce five types of training objectives to realize the three challenging tasks at the same time. The experimental results show that our architecture can be adaptive well to full transfer learning and partial transfer learning upon a well-learned disentangled representation. Besides, the trained network also demonstrates high potential to generate style-transferred images.
Abstract (translated)
最近已经提出了许多方法来解决域适应问题。然而,它们的成功隐含地基于这样的假设:域的信息是完全可转移的。如果不满足该假设,则负转移的影响可能降低域适应性。在本文中,通过考虑三个任务 - 域适应,解开表示和风格转移同时提出了一个更好的学习网络。首先,将学到的特征分解为共同的部分和特定的部分。公共部分代表可转移特征,适用于具有较少负转移的域适应。相反,特定部分表征每个域的独特风格。在此基础上,介绍了跨域特征交换的新概念,不仅可以增强共同特征的可转移性,而且可以用于图像样式转移。这些设计使我们能够引入五种类型的培训目标,同时实现三项具有挑战性的任务。实验结果表明,我们的体系结构可以很好地适应完全转移学习和部分转移学习的良好学习解开表示。此外,经过训练的网络也展示了生成风格转移图像的高潜力。
URL
https://arxiv.org/abs/1712.09025