Related papers: UniTSFace: Unified Threshold Integrated Sample-to-…

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…

Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images. The key challenge in FSS is to classify the labels of query pixels using…

Modern face recognition systems remain vulnerable to spoofing attempts, including both physical presentation attacks and digital forgeries. Traditionally, these two attack vectors have been handled by separate models, each targeting its own…

In face recognition, designing margin-based (e.g., angular, additive, additive angular margins) softmax loss functions plays an important role in learning discriminative features. However, these hand-crafted heuristic methods are…

SARS-CoV-2 has presented direct and indirect challenges to the scientific community. One of the most prominent indirect challenges advents from the mandatory use of face masks in a large number of countries. Face recognition methods…

Face anti-spoofing (FAS) is an essential mechanism for safeguarding the integrity of automated face recognition systems. Despite substantial advancements, the generalization of existing approaches to real-world applications remains…

Empirical risk minimization (ERM) with a computationally feasible surrogate loss is a widely accepted approach for classification. Notably, the convexity and calibration (CC) properties of a loss function ensure consistency of ERM in…

Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations such as pose, illumination, viewpoint, background, and sensor noise. Recent approaches…

Current image-text retrieval methods have demonstrated impressive performance in recent years. However, they still face two problems: the inter-modal matching missing problem and the intra-modal semantic loss problem. These problems can…

Despite the potential of federated learning in medical applications, inconsistent imaging quality across institutions-stemming from lower-quality data from a minority of clients-biases federated models toward more common high-quality…

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…

Driven by advancements in deep learning, computer-aided diagnoses have made remarkable progress. However, outside controlled laboratory settings, algorithms may encounter several challenges. In the medical domain, these difficulties often…

Open-set face recognition refers to a scenario in which biometric systems have incomplete knowledge of all existing subjects. Therefore, they are expected to prevent face samples of unregistered subjects from being identified as previously…

Face anti-spoofing (FAS) plays a pivotal role in ensuring the security and reliability of face recognition systems. With advancements in vision-language pretrained (VLP) models, recent two-class FAS techniques have leveraged the advantages…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

We motivate and present Ring loss, a simple and elegant feature normalization approach for deep networks designed to augment standard loss functions such as Softmax. We argue that deep feature normalization is an important aspect of…

Most deep neural networks (DNNs) based ultrasound (US) medical image analysis models use pretrained backbones (e.g., ImageNet) for better model generalization. However, the domain gap between natural and medical images causes an inevitable…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

Semi-Supervised Learning (SSL) is important for reducing the annotation cost for medical image segmentation models. State-of-the-art SSL methods such as Mean Teacher, FixMatch and Cross Pseudo Supervision (CPS) are mainly based on…

In recent years, Face Anti-Spoofing (FAS) has played a crucial role in preserving the security of face recognition technology. With the rise of counterfeit face generation techniques, the challenge posed by digitally edited faces to face…