Related papers: Learning the Roots of Visual Domain Shift

The phenomenon of data distribution evolving over time has been observed in a range of applications, calling the needs of adaptive learning algorithms. We thus study the problem of supervised gradual domain adaptation, where labeled data…

It is vital to learn effective policies that can be transferred to different domains with dynamics discrepancies in reinforcement learning (RL). In this paper, we consider dynamics adaptation settings where there exists dynamics mismatch…

Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth estimation) has the…

Deep neural networks are widely used in image classification problems. However, little work addresses how features from different deep neural networks affect the domain adaptation problem. Existing methods often extract deep features from…

Domain adaptation is a key feature in Machine Translation. It generally encompasses terminology, domain and style adaptation, especially for human post-editing workflows in Computer Assisted Translation (CAT). With Neural Machine…

Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a…

Due to the existence of dataset shifts, the distributions of data acquired from different working conditions show significant differences in real-world industrial applications, which leads to performance degradation of traditional machine…

Deep neural networks have demonstrated impressive performance in various machine learning tasks. However, they are notoriously sensitive to changes in data distribution. Often, even a slight change in the distribution can lead to drastic…

Domain adaptation considers the problem of generalising a model learnt using data from a particular source domain to a different target domain. Often it is difficult to find a suitable single source to adapt from, and one must consider…

Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be able to compare the strength of each property between images,…

Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain. However, it is still not clear what factors affect the success of domain…

In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for fine-grained scene recognition. We first…

Technological developments call for increasing perception and action capabilities of robots. Among other skills, vision systems that can adapt to any possible change in the working conditions are needed. Since these conditions are…

Though vision transformers (ViTs) have exhibited impressive ability for representation learning, we empirically find that they cannot generalize well to unseen domains with previous domain generalization algorithms. In this paper, we…

Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing methods use global-level feature alignment to transfer the…

Domain adaptation is crucial in many real-world applications where the distribution of the training data differs from the distribution of the test data. Previous Deep Learning-based approaches to domain adaptation need to be trained jointly…

Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target…

Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains. We present a study of various distance-based…

Machine learning systems must adapt to data distributions that evolve over time, in applications ranging from sensor networks and self-driving car perception modules to brain-machine interfaces. We consider gradual domain adaptation, where…

While deep learning has led to significant advances in visual recognition over the past few years, such advances often require a lot of annotated data. Unsupervised domain adaptation has emerged as an alternative approach that does not…