Related papers: Disentangled Source-Free Personalization for Facia…
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…
Unsupervised domain adaptation (UDA) generally aligns the unlabeled target domain data to the distribution of the source domain to mitigate the distribution shift problem. The standard UDA requires sharing the source data with the target,…
Heterogeneous Face Recognition (HFR) refers to matching face images captured in different domains, such as thermal to visible images (VIS), sketches to visible images, near-infrared to visible, and so on. This is particularly useful in…
The performance of a convolutional neural network (CNN) based face recognition model largely relies on the richness of labelled training data. Collecting a training set with large variations of a face identity under different poses and…
Deep learning models are sensitive to domain shift phenomena. A model trained on images from one domain cannot generalise well when tested on images from a different domain, despite capturing similar anatomical structures. It is mainly…
Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces. Despite these…
Dynamic Facial Expression Recognition (DFER) plays a critical role in affective computing and human-computer interaction. Although existing methods achieve comparable performance, they inevitably suffer from performance degradation under…
Growing demands for clinical data privacy and storage constraints have spurred advances in Source Free Unsupervised Domain Adaptation (SFUDA). SFUDA addresses the domain shift by adapting models from the source domain to the unseen target…
Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features. However, a linear model with just several parameters…
Cross-domain face retargeting requires disentangled control over identity, expressions, and domain-specific stylistic attributes. Existing methods, typically trained on real-world faces, either fail to generalize across domains, need…
Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera…
Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be…
Conventional Domain Adaptation (DA) methods aim to learn domain-invariant feature representations to improve the target adaptation performance. However, we motivate that domain-specificity is equally important since in-domain trained models…
Facial expression analysis is central to understanding human behavior, yet existing coding systems such as the Facial Action Coding System (FACS) are constrained by limited coverage and costly manual annotation. In this work, we introduce…
Semi-supervised domain adaptation (SSDA) has been widely studied due to its ability to utilize a few labeled target data to improve the generalization ability of the model. However, existing methods only consider designing certain…
As face recognition is widely used in diverse security-critical applications, the study of face anti-spoofing (FAS) has attracted more and more attention. Several FAS methods have achieved promising performances if the attack types in the…
Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms. Existing approaches…
Automatic Facial Expression Recognition (FER) has attracted increasing attention in the last 20 years since facial expressions play a central role in human communication. Most FER methodologies utilize Deep Neural Networks (DNNs) that are…
Developing computational pathology models is essential for reducing manual tissue typing from whole slide images, transferring knowledge from the source domain to an unlabeled, shifted target domain, and identifying unseen categories. We…
Unsupervised Domain Adaptation~(UDA) has attracted a surge of interest over the past decade but is difficult to be used in real-world applications. Considering the privacy-preservation issues and security concerns, in this work, we study a…