Recent advancements in domain generalization (DG) for face anti-spoofing (FAS) have
garnered considerable attention. Traditional methods have focused on designing learning …

Real-world tasks are universally associated with training samples that exhibit a long-tailed
class distribution, and traditional deep learning models are not suitable for fitting this …

Deep neural networks are vulnerable to adversarial attacks leading to erroneous outputs.
Adversarial training has been recognized as one of the most effective methods to counter …

Recently, using deep learning to achieve WiFi-based human activity recognition (HAR) has
drawn significant attention. While capable of achieving accurate identification in a single …

Retinal vessel segmentation is crucial for diagnosing and monitoring various eye diseases
such as diabetic retinopathy, glaucoma, and hypertension. In this study, we examine how …

Recently, the continuous evolution of deep learning has opened up promising avenues to
groundbreaking advancements in wireless sensing systems, which significantly enhance the …

Real-world image classification data usually exhibits a challenging long-tailed distribution,
attributed to the inherent difficulty in data collection. Existing ensemble approaches …

Real-world data often exhibits a long-tailed distribution, where the number of training
samples for head classes far exceeds that of tail classes. This class imbalance phenomenon …

AI-aided financial regulation (AIFR) is a practical and significant task, but current solutions
have yet to be optimized with customized model designs. Given the privacy concerns …

Long-tailed data distributions have been a major challenge for the practical application of
deep learning. Information augmentation intends to expand the long-tailed data into uniform …