论文标题
吸引，敏感和探索：学习半监督域适应的功能对齐网络
Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
论文作者
论文摘要
尽管在几个计算机视觉任务中广泛采用了无监督的域适应方法，但如果我们可以利用来自真实应用程序中遇到的新域中的一些标记数据，则更为可取。半监督域适应（SSDA）问题的新颖设置与域的适应问题和半监督的学习问题分享了挑战。但是，最近的一项研究表明，常规领域的适应性和半监督学习方法通常会导致SSDA问题有效或负转移较低。为了解释观察结果并解决了SSDA问题，在本文中，我们提出了目标域内的域内差异问题，到目前为止，该问题从未进行过。然后，我们证明解决域内差异会导致SSDA问题的最终目标。我们提出了一个SSDA框架，旨在通过缓解内域差异来对齐特征。我们的框架主要由三个方案组成，即吸引，扰动和探索。首先，吸引力方案在全球范围内最大程度地减少了目标域内的内域差异。其次，我们证明了常规的对抗扰动方法与SSDA的不相容性。然后，我们提出了一个域自适应对抗扰动方案，该方案以减少域内差异的方式将给定的目标样本散布。最后，探索方案通过选择性地对准未标记的目标特征互补的扰动方案，以互补的方式与吸引方案相辅相成。我们对域适应基准数据集进行了广泛的实验，例如Domainnet，Office-Home和Office。我们的方法可以在所有数据集上实现最先进的性能。
Although unsupervised domain adaptation methods have been widely adopted across several computer vision tasks, it is more desirable if we can exploit a few labeled data from new domains encountered in a real application. The novel setting of the semi-supervised domain adaptation (SSDA) problem shares the challenges with the domain adaptation problem and the semi-supervised learning problem. However, a recent study shows that conventional domain adaptation and semi-supervised learning methods often result in less effective or negative transfer in the SSDA problem. In order to interpret the observation and address the SSDA problem, in this paper, we raise the intra-domain discrepancy issue within the target domain, which has never been discussed so far. Then, we demonstrate that addressing the intra-domain discrepancy leads to the ultimate goal of the SSDA problem. We propose an SSDA framework that aims to align features via alleviation of the intra-domain discrepancy. Our framework mainly consists of three schemes, i.e., attraction, perturbation, and exploration. First, the attraction scheme globally minimizes the intra-domain discrepancy within the target domain. Second, we demonstrate the incompatibility of the conventional adversarial perturbation methods with SSDA. Then, we present a domain adaptive adversarial perturbation scheme, which perturbs the given target samples in a way that reduces the intra-domain discrepancy. Finally, the exploration scheme locally aligns features in a class-wise manner complementary to the attraction scheme by selectively aligning unlabeled target features complementary to the perturbation scheme. We conduct extensive experiments on domain adaptation benchmark datasets such as DomainNet, Office-Home, and Office. Our method achieves state-of-the-art performances on all datasets.
