Related papers: Fast and Reliable Probabilistic Face Embeddings in…
Face recognition systems have to deal with large variabilities (such as different poses, illuminations, and expressions) that might lead to incorrect matching decisions. These variabilities can be measured in terms of face image quality…
Federated learning (FL) is an emerging distributed machine learning paradigm that avoids data sharing among training nodes so as to protect data privacy. Under coordination of the FL server, each client conducts model training using its own…
Face recognition technology has been deployed in various real-life applications. The most sophisticated deep learning-based face recognition systems rely on training millions of face images through complex deep neural networks to achieve…
Personalized Federated Learning (PFL) enables a collection of agents to collaboratively learn individual models without sharing raw data. We propose a new PFL approach in which each agent optimizes a weighted combination of all agents'…
The common implementation of face recognition systems as a cascade of a detection stage and a recognition or verification stage can cause problems beyond failures of the detector. When the detector succeeds, it can detect faces that cannot…
Automatic head frontal-view identification is challenging due to appearance variations caused by pose changes, especially without any training samples. In this paper, we present an unsupervised algorithm for identifying frontal view among…
We propose an efficient algorithm for approximate computation of the profile maximum likelihood (PML), a variant of maximum likelihood maximizing the probability of observing a sufficient statistic rather than the empirical sample. The PML…
Pattern recognition applications often suffer from skewed data distributions between classes, which may vary during operations w.r.t. the design data. Two-class classification systems designed using skewed data tend to recognize the…
Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their captions, the multiplicity of the correspondences makes the…
In recent years, mixup regularization has gained popularity as an effective way to improve the generalization performance of deep learning models by training on convex combinations of training data. While many mixup variants have been…
With the advancement of face recognition (FR) systems, privacy-preserving face recognition (PPFR) systems have gained popularity for their accurate recognition, enhanced facial privacy protection, and robustness to various attacks. However,…
Despite the great success achieved by deep learning methods in face recognition, severe performance drops are observed for large pose variations in unconstrained environments (e.g., in cases of surveillance and photo-tagging). To address…
Machine learning based partial differential equations (PDEs) solvers have received great attention in recent years. Most progress in this area has been driven by deep neural networks such as physics-informed neural networks (PINNs) and…
Mixture of Experts (MoE) are successful models for modeling heterogeneous data in many statistical learning problems including regression, clustering and classification. Generally fitted by maximum likelihood estimation via the well-known…
Plastic surgery and disguise variations are two of the most challenging co-variates of face recognition. The state-of-art deep learning models are not sufficiently successful due to the availability of limited training samples. In this…
Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative…
In the field of face recognition, a model learns to distinguish millions of face images with fewer dimensional embedding features, and such vast information may not be properly encoded in the conventional model with a single branch. We…
With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…
Probabilistic classifiers output confidence scores along with their predictions, and these confidence scores should be calibrated, i.e., they should reflect the reliability of the prediction. Confidence scores that minimize standard metrics…
We study streaming data with categorical features where the vocabulary of categorical feature values is changing and can even grow unboundedly over time. Feature hashing is commonly used as a pre-processing step to map these categorical…