Related papers: Modeling Uncertain Feature Representation for Doma…

Understanding why deep neural networks (DNNs) fail to generalize to unseen samples remains a long-standing challenge. Existing studies mainly examine changes in externally observable factors such as data, representations, or outputs, yet…

Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data. Domain generalization aims at tackling this problem by learning transferable knowledge from…

Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem…

Domain generalization (DG), aiming at models able to work on multiple unseen domains, is a must-have characteristic of general artificial intelligence. DG based on single source domain training data is more challenging due to the lack of…

In the past decade, deep convolutional neural networks have achieved significant success in image classification and ranking and have therefore found numerous applications in multimedia content retrieval. Still, these models suffer from…

Domain generalization aims to enhance the model robustness against domain shift without accessing the target domain. Since the available source domains for training are limited, recent approaches focus on generating samples of novel…

Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g.…

Modeling data uncertainty is important for noisy images, but seldom explored for face recognition. The pioneer work, PFE, considers uncertainty by modeling each face image embedding as a Gaussian distribution. It is quite effective.…

We study a worst-case scenario in generalization: Out-of-domain generalization from a single source. The goal is to learn a robust model from a single source and expect it to generalize over many unknown distributions. This challenging…

Understanding how feature learning affects generalization is among the foremost goals of modern deep learning theory. Here, we study how the ability to learn representations affects the generalization performance of a simple class of…

Machine learning algorithms have revolutionized different fields, including natural language processing, computer vision, signal processing, and medical data processing. Despite the excellent capabilities of machine learning algorithms in…

Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain. In this paper, we propose to tackle the problem of domain generalization by delivering an effective framework named Variational…

Domain adaption (DA) and domain generalization (DG) are two closely related methods which are both concerned with the task of assigning labels to an unlabeled data set. The only dissimilarity between these approaches is that DA can access…

The objective of domain generalization (DG) is to enable models to be robust against domain shift. DG is crucial for deploying vision-language models (VLMs) in real-world applications, yet most existing methods rely on domain labels that…

We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model…

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample,…

Machine learning models rely on various assumptions to attain high accuracy. One of the preliminary assumptions of these models is the independent and identical distribution, which suggests that the train and test data are sampled from the…

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…

Convolutional Neural Networks (CNNs) show impressive performance in the standard classification setting where training and testing data are drawn i.i.d. from a given domain. However, CNNs do not readily generalize to new domains with…