Related papers: AdvST: Revisiting Data Augmentations for Single Do…

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…

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…

Domain adaptation has been widely explored by transferring the knowledge from a label-rich source domain to a related but unlabeled target domain. Most existing domain adaptation algorithms attend to adapting feature representations across…

Most recent self-supervised learning methods learn visual representation by contrasting different augmented views of images. Compared with supervised learning, more aggressive augmentations have been introduced to further improve the…

Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set. To alleviate the effect of `domain shift', the major challenge in domain adaptation,…

We tackle the challenging problem of single-source domain generalization (DG) for medical image segmentation, where we train a network on one domain (e.g., CT) and directly apply it to a different domain (e.g., MR) without adapting the…

Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess…

Semantic segmentation in a supervised learning manner has achieved significant progress in recent years. However, its performance usually drops dramatically due to the data-distribution discrepancy between seen and unseen domains when we…

Data augmentation is a ubiquitous technique used to provide robustness to automatic speech recognition (ASR) training. However, even as so much of the ASR training process has become automated and more "end-to-end", the data augmentation…

Contemporary domain adaptive semantic segmentation aims to address data annotation challenges by assuming that target domains are completely unannotated. However, annotating a few target samples is usually very manageable and worthwhile…

Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge…

Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even…

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…

As one of the fundamental tasks in computer vision, semantic segmentation plays an important role in real world applications. Although numerous deep learning models have made notable progress on several mainstream datasets with the rapid…

Domain generalization (DG) has been a hot topic in image recognition, with a goal to train a general model that can perform well on unseen domains. Recently, federated learning (FL), an emerging machine learning paradigm to train a global…

Domain Generalization (DG) aims to enhance model robustness in unseen or distributionally shifted target domains through training exclusively on source domains. Although existing DG techniques, such as data manipulation, learning…

Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all…

Data augmentation is often used to enlarge datasets with synthetic samples generated in accordance with the underlying data distribution. To enable a wider range of augmentations, we explore negative data augmentation strategies (NDA)that…

Domain generalization (DG) aims to learn predictive models that can generalize to unseen domains. Most existing DG approaches focus on learning domain-invariant representations under the assumption of conditional distribution shift (i.e.,…

Domain generalization (DG) task aims to learn a robust model from source domains that could handle the out-of-distribution (OOD) issue. In order to improve the generalization ability of the model in unseen domains, increasing the diversity…