Domain generalization (DG) deals with the problem of domain shift where a machine learning model trained on multiple-source domains fail to generalize well on a target domain with different statistics. Multiple approaches have been proposed to solve the problem of domain generalization by learning domain invariant representations across the source domains that fail to guarantee generalization on the shifted target domain. We propose a Generative Nearest Neighbor based Discrepancy Minimization (GNNDM) method which provides a theoretical guarantee that is upper bounded by the error in the labeling process of the target. We employ a Domain Discrepancy Minimization Network (DDMN) that learns domain agnostic features to produce a single source domain while preserving the class labels of the data points. Features extracted from this source domain are learned using a generative model whose latent space is used as a sampler to retrieve the nearest neighbors for the target data points. The proposed method does not require access to the domain labels (a more realistic scenario) as opposed to the existing approaches. Empirically, we show the efficacy of our method on two datasets: PACS and VLCS. Through extensive experimentation, we demonstrate the effectiveness of the proposed method that outperforms several state-of-the-art DG methods.
Discrepancy Minimization Improves Cross-Hospital Robustness in Digital Pathology
Reichman University, Herzliya, Israel（以色列海法大学）；Institute of Pathology, Sheba Medical Center, Ramat-Gan, Israel（以色列沙巴医疗中心病理研究所）；Technion - Israel Institute of Technology, Haifa, Israel（以色列技术学院）
虽然取得了显著的进展，但在没有任何标记数据的情况下，很难诱导出有监督的分类器。无监督的领域自适应能够通过将知识从标记的源域转移到未标记的目标域来克服这一挑战。可转移性和可区分性是表征特征表示的优越性的两个关键标准，以实现成功的领域自适应。在本文中，一种新的方法称为\textit{learning TransFerable and Discriminative Features for unsupervised domain adaptation}（TFDF）提出了这两个目标同时优化。一方面，进行分布对齐以减少域差异并学习更多的可传递表示。在再生核希尔伯特空间（RKHS）中，我们采用了一种新的统计量\textit{Maximum Mean and Covariance Discrepancy}（MMCD），它不仅能捕获一阶统计信息，还能捕获二阶统计信息，而不是采用仅捕获一阶统计信息的\textit{Maximum Mean Discrepancy}（MMD）来度量分布差异.另一方面，我们建议通过流形正则化探索局部判别信息，并通过最小化所提出的\textit{class confusion}目标来学习更多的判别特征，分别探索全局判别信息。我们将这两个目标集成到\textit{Structural Risk Minimization}（RSM）框架中，并学习域不变分类器。在5个真实数据集…
Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）；Huawei Technologies（华为技术有限公司）
