Related papers: Learning Factorized Representations for Open-set D…

Modern machine learning (ML) models are becoming increasingly popular and are widely used in decision-making systems. However, studies have shown critical issues of ML discrimination and unfairness, which hinder their adoption on high-stake…

Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has…

In practice, and especially when training deep neural networks, visual recognition rules are often learned based on various sources of information. On the other hand, the recent deployment of facial recognition systems with uneven…

Recently unsupervised person re-identification (re-ID) has drawn much attention due to its open-world scenario settings where limited annotated data is available. Existing supervised methods often fail to generalize well on unseen domains,…

Anomaly Detection is an important problem within computer vision, having variety of real-life applications. Yet, the current set of solutions to this problem entail known, systematic shortcomings. Specifically, contemporary surface Anomaly…

Multi-source domain adaptation aims to reduce performance degradation when applying machine learning models to unseen domains. A fundamental challenge is devising the optimal strategy for feature selection. Existing literature is somewhat…

Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with…

In many real-world classification or recognition tasks, it is often difficult to collect training examples that exhaust all possible classes due to, for example, incomplete knowledge during training or ever changing regimes. Therefore,…

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels. While the field has seen extensive methodological development, its…

Most existing unsupervised domain adaptation methods mainly focused on aligning the marginal distributions of samples between the source and target domains. This setting does not sufficiently consider the class distribution information…

Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of labelling information in target domain. They are…

Despite rapid advances in face recognition, there remains a clear gap between the performance of still image-based face recognition and video-based face recognition, due to the vast difference in visual quality between the domains and the…

Domain adaptation, a pivotal branch of transfer learning, aims to enhance the performance of machine learning models when deployed in target domains with distinct data distributions. This is particularly critical for object detection tasks,…

We present a low-rank transformation approach to compensate for face variations due to changes in visual domains, such as pose and illumination. The key idea is to learn discriminative linear transformations for face images using matrix…

We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning. The core idea is to consider the predictions of a source domain network on target domain data as noisy labels, and learn a…

In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e.g. same classes), but also different latent…

Contrastive learning is a highly effective method for learning representations from unlabeled data. Recent works show that contrastive representations can transfer across domains, leading to simple state-of-the-art algorithms for…

We investigate the power of censoring techniques, first developed for learning {\em fair representations}, to address domain generalization. We examine {\em adversarial} censoring techniques for learning invariant representations from…

Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy. However, it is not always feasible to obtain high-quality supervisory signals from users, especially for vision…