Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

Metric learning aims to measure the similarity among samples while using an optimal
distance metric for learning tasks. Metric learning methods, which generally use a linear …

Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so
that the attacked models perform well on benign samples, whereas their predictions will be …

This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming
to maximize the within-class similarity s_p and minimize the between-class similarity s_n …

We propose a new method to detect deepfake images using the cue of the source feature
inconsistency within the forged images. It is based on the hypothesis that images' distinct …

In this paper, we contribute a new million-scale face benchmark containing noisy 4M
identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) …

Deep learning, in particular the deep convolutional neural networks, has received
increasing interests in face recognition recently, and a number of deep learning methods …

Face recognition has made extraordinary progress owing to the advancement of deep
convolutional neural networks (CNNs). The central task of face recognition, including face …

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 …

With the prevalent use of Deep Neural Networks (DNNs) in many applications, security of
these networks is of importance. Pre-trained DNNs may contain backdoors that are injected …