3 papers
cs.CV2026
TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks
Mengda Xie, Yiling He, Meie Fang
Multi-threat robustness remains a fundamental challenge in deep learning. Although joint adversarial training (JAT) is widely adopted, it suffers from negative transfer under heter…
cs.CV2025
Boosting Illuminant Estimation in Deep Color Constancy through Enhancing Brightness Robustness
Mengda Xie, Chengzhi Zhong, Yiling He +2
Color constancy estimates illuminant chromaticity to correct color-biased images. Recently, Deep Neural Network-driven Color Constancy (DNNCC) models have made substantial advancem…
cs.CV2023
RetouchUAA: Unconstrained Adversarial Attack via Image Retouching
Mengda Xie, Yiling He, Meie Fang
Deep Neural Networks (DNNs) are susceptible to adversarial examples. Conventional attacks generate controlled noise-like perturbations that fail to reflect real-world scenarios and…