Gradient alignment for cross-domain face anti-spoofing
Recent advancements in domain generalization (DG) for face anti-spoofing (FAS) have
garnered considerable attention. Traditional methods have focused on designing learning …
garnered considerable attention. Traditional methods have focused on designing learning …
Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed 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 …
class distribution, and traditional deep learning models are not suitable for fitting this …
Revisiting Adversarial Training under Long-Tailed Distributions
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 …
Adversarial training has been recognized as one of the most effective methods to counter …
i-Sample: Augment domain adversarial adaptation models for WiFi-Based HAR
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 …
drawn significant attention. While capable of achieving accurate identification in a single …
A Retinal Vessel Segmentation Method Based on the Sharpness-Aware Minimization Model
I Mariam, X Xue, K Gadson - Sensors, 2024 - mdpi.com
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 …
such as diabetic retinopathy, glaucoma, and hypertension. In this study, we examine how …
SAT: A Selective Adversarial Training Approach for WiFi-based Human Activity Recognition
Recently, the continuous evolution of deep learning has opened up promising avenues to
groundbreaking advancements in wireless sensing systems, which significantly enhance the …
groundbreaking advancements in wireless sensing systems, which significantly enhance the …
Multiple Contrastive Experts for long-tailed image classification
Real-world image classification data usually exhibits a challenging long-tailed distribution,
attributed to the inherent difficulty in data collection. Existing ensemble approaches …
attributed to the inherent difficulty in data collection. Existing ensemble approaches …
Feature balanced re-enhanced network with multi-factor margin loss for long-tailed visual recognition
Y Wang, J Zhai - Neurocomputing, 2024 - Elsevier
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 …
samples for head classes far exceeds that of tail classes. This class imbalance phenomenon …
Enhancing Fitness Evaluation in Genetic Algorithm-Based Architecture Search for AI-Aided Financial Regulation
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 …
have yet to be optimized with customized model designs. Given the privacy concerns …
ChatDiff: A ChatGPT-based diffusion model for long-tailed classification
C Deng, D Li, L Ji, C Zhang, B Li, H Yan, J Zheng… - Neural Networks, 2024 - Elsevier
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 …
deep learning. Information augmentation intends to expand the long-tailed data into uniform …