论文标题
BP-Triplet网络无监督域的适应性：贝叶斯的观点
BP-Triplet Net for Unsupervised Domain Adaptation: A Bayesian Perspective
论文作者
论文摘要
三胞胎损失是深度度量学习（DML）方法之一，是学习嵌入的嵌入，其中同一班级的示例比不同类别的示例更接近。由DML促进，我们从贝叶斯学习的角度提出了无监督的域适应性（UDA）的有效BP-Triplet损失，并将该模型称为BP-Triplet Net。在以前的UDA基于度量学习的方法中，跨域的样本对被平等处理，这是由于域偏差而不合适的。在我们的工作中，考虑到配对样本在特征学习和领域对齐方面的不同重要性，我们从贝叶斯学习的角度推断出BP-Triplet损失有效UDA。我们的BP-三局损失调节了域内和间域中的配对样品的权重。尤其是，它可以自我参加硬对（包括硬阳性对和硬性负面对）。连同常用的域对齐对抗性损失，目标伪标签的质量逐渐改善。我们的方法达到了理想源和目标假设的低关节误差。然后，在Ben-David S定理之后，可以将预期的目标误差在上限。对五个基准数据集，手写数字，Office31，Imageclef-DA，Office-Home和Visda-2017的全面评估证明了UDA建议方法的有效性。
Triplet loss, one of the deep metric learning (DML) methods, is to learn the embeddings where examples from the same class are closer than examples from different classes. Motivated by DML, we propose an effective BP-Triplet Loss for unsupervised domain adaption (UDA) from the perspective of Bayesian learning and we name the model as BP-Triplet Net. In previous metric learning based methods for UDA, sample pairs across domains are treated equally, which is not appropriate due to the domain bias. In our work, considering the different importance of pair-wise samples for both feature learning and domain alignment, we deduce our BP-Triplet loss for effective UDA from the perspective of Bayesian learning. Our BP-Triplet loss adjusts the weights of pair-wise samples in intra domain and inter domain. Especially, it can self attend to the hard pairs (including hard positive pair and hard negative pair). Together with the commonly used adversarial loss for domain alignment, the quality of target pseudo labels is progressively improved. Our method achieved low joint error of the ideal source and target hypothesis. The expected target error can then be upper bounded following Ben-David s theorem. Comprehensive evaluations on five benchmark datasets, handwritten digits, Office31, ImageCLEF-DA, Office-Home and VisDA-2017 demonstrate the effectiveness of the proposed approach for UDA.
