Synthetic data is gaining increasing relevance for training machine learning models. This is
mainly motivated due to several factors such as the lack of real data and intra-class …

Face recognition technology, though undeniably transformative in its technical evolution,
remains conspicuously underleveraged in humanitarian endeavors. This survey highlights …

Cooperative palmprint recognition, pivotal for civilian and commercial uses, stands as the
most essential and broadly demanded branch in biometrics. These applications, often tied to …

Abstract Clustering-based Pseudo-Labels (PLs) are widely used to optimize Speaker
Embedding (SE) networks and train Self-Supervised (SS) Speaker Verification (SV) systems …

The field of face recognition (FR) has undergone significant advancements with the rise of
deep learning. Recently, the success of unsupervised learning and graph neural networks …

Adversarial perturbation is a severe threat to deep learning-based systems such as
classification and recognition because it makes the system output wrong answers …

This paper introduces the concept of uniform classification, which employs a unified
threshold to classify all samples rather than adaptive threshold classifying each individual …

Recognition of low-quality face images remains a challenge due to invisible or deformation
in partial facial regions. For low-quality images dominated by missing partial facial regions …

A crucial assumption underlying the most current theory of machine learning is that the
training distribution is identical to the test distribution. However, this assumption may not …

We propose the linearly adaptive cross entropy loss function. This is a novel measure
derived from the information theory. In comparison to the standard cross entropy loss …