Deep learning applies multiple processing layers to learn representations of data with
multiple levels of feature extraction. This emerging technique has reshaped the research …

Biometric systems have the goal of measuring and analyzing the unique physical or
behavioral characteristics of an individual. The main feature of biometric systems is the use …

Large text-to-image diffusion models have impressive capabilities in generating
photorealistic images from text prompts. How to effectively guide or control these powerful …

One of the main challenges in feature learning using Deep Convolutional Neural Networks
(DCNNs) for large-scale face recognition is the design of appropriate loss functions that can …

In this letter, we propose a conceptually simple and intuitive learning objective function, ie,
additive margin softmax, for face verification. In general, face verification tasks can be …

A fundamental challenge for machine learning models is generalizing to out-of-distribution
(OOD) data, in part due to spurious correlations. To tackle this challenge, we first formalize …

Face recognition is one of the most common biometric authentication methods as its
feasibility while convenient use. Recently, the COVID-19 pandemic is dramatically …

The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning
models. But although the default choice of a Gaussian distribution for both the prior and …

Person Re-identification (re-ID) has great potential to contribute to video surveillance that
automatically searches and identifies people across different cameras. Heterogeneous …

We present a new direction for increasing the interpretability of deep neural networks
(DNNs) by promoting weight-input alignment during training. For this, we propose to replace …