论文标题
通过角不变性镜头的域概括
Domain Generalization through the Lens of Angular Invariance
论文作者
论文摘要
域的概括（DG）旨在将在多个源域训练的分类器推广到具有域移动的看不见的目标域。现有DG文献中的一个普遍的主题是具有各种不变性假设的域不变的表示学习。但是，先前的工作将自己限制为对现实世界挑战的根本假设：如果由深神经网络（DNN）引起的映射可以很好地对齐源域，则这样的映射也可以使目标域保持一致。在本文中，我们只是将DNN作为特征提取器，以放宽分布对齐的要求。具体而言，我们提出了一种新型的角度不变性和随附的规范移位假设。根据建议的不变性项，我们提出了一种新型的深DG方法，称为角不变域泛化网络（AIDGN）。 AIDGN的优化目标是通过Von-Mises Fisher（VMF）混合模型开发的。在多个DG基准数据集上进行的广泛实验验证了所提出的AIDGN方法的有效性。
Domain generalization (DG) aims at generalizing a classifier trained on multiple source domains to an unseen target domain with domain shift. A common pervasive theme in existing DG literature is domain-invariant representation learning with various invariance assumptions. However, prior works restrict themselves to a radical assumption for realworld challenges: If a mapping induced by a deep neural network (DNN) could align the source domains well, then such a mapping aligns a target domain as well. In this paper, we simply take DNNs as feature extractors to relax the requirement of distribution alignment. Specifically, we put forward a novel angular invariance and the accompanied norm shift assumption. Based on the proposed term of invariance, we propose a novel deep DG method called Angular Invariance Domain Generalization Network (AIDGN). The optimization objective of AIDGN is developed with a von-Mises Fisher (vMF) mixture model. Extensive experiments on multiple DG benchmark datasets validate the effectiveness of the proposed AIDGN method.
