58 citations · 75 across the 4 of their papers we have counts for
4 papers
Towards Effective Image Manipulation Detection with Proposal Contrastive Learning
Yuyuan Zeng, Bowen Zhao, Shanzhao Qiu +2
Deep models have been widely and successfully used in image manipulation detection, which aims to classify tampered images and localize tampered regions. Most existing methods main…
Improving Adversarial Robustness via Channel-wise Activation Suppressing
Yang Bai, Yuyuan Zeng, Yong Jiang +3
The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs). Different from existing…
Improving Query Efficiency of Black-box Adversarial Attack
Yang Bai, Yuyuan Zeng, Yong Jiang +3
Deep neural networks (DNNs) have demonstrated excellent performance on various tasks, however they are under the risk of adversarial examples that can be easily generated when the…
Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
Haoyu Liang, Zhihao Ouyang, Yuyuan Zeng +5
Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as "black-box" and lack of interpretability. One main reason is…