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 …

The virtual-to-real paradigm, ie, training models on virtual data and then applying them to
solve real-world problems, has attracted more and more attention from various domains by …

Recognition in low quality face datasets is challenging because facial attributes are
obscured and degraded. Advances in margin-based loss functions have resulted in …

Recently, deep neural networks (DNNs) promote mainly by network architectures and loss
functions; however, the development of neuron models has been quite limited. In this study …

Abstract Noisy label Facial Expression Recognition (FER) is more challenging than
traditional noisy label classification tasks due to the inter-class similarity and the annotation …

Recent advances in deep neural networks (DNNs) have mainly focused on innovations in
network architecture and loss function. In this paper, we introduce a flexible high-order …

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 …

Learning discriminative deep feature embeddings by using million-scale in-the-wild datasets
and margin-based softmax loss is the current state-of-the-art approach for face recognition …

Face recognition (FR) is one of the most popular and long-standing topics in computer
vision. With the recent development of deep learning techniques and large-scale datasets …

Fine-grained object recognition (FGOR) aims to learn discriminative features that can
identify the subtle distinctions between visually similar objects. However, less effort has …