485 citations · 1.1k across the 52 of their papers we have counts for
7 papers · 1 filter
On the Generalization of Multi-modal Contrastive Learning
Qi Zhang, Yifei Wang, Yisen Wang
Multi-modal contrastive learning (MMCL) has recently garnered considerable interest due to its superior performance in visual tasks, achieved by embedding multi-modal data, such as…
Generalist: Decoupling Natural and Robust Generalization
Hongjun Wang, Yisen Wang
Deep neural networks obtained by standard training have been constantly plagued by adversarial examples. Although adversarial training demonstrates its capability to defend against…
When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture
Yichuan Mo, Dongxian Wu, Yifei Wang +2
Vision Transformers (ViTs) have recently achieved competitive performance in broad vision tasks. Unfortunately, on popular threat models, naturally trained ViTs are shown to provid…
GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling
Chen Chen, Yisen Wang, Honghua Chen +6
Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding.Despite of significant advances in recent years, most…
Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks
Chen Ma, Xiangyu Guo, Li Chen +2
One major problem in black-box adversarial attacks is the high query complexity in the hard-label attack setting, where only the top-1 predicted label is available. In this paper,…
Moiré Attack (MA): A New Potential Risk of Screen Photos
Dantong Niu, Ruohao Guo, Yisen Wang
Images, captured by a camera, play a critical role in training Deep Neural Networks (DNNs). Usually, we assume the images acquired by cameras are consistent with the ones perceived…
Analysis and Applications of Class-wise Robustness in Adversarial Training
Qi Tian, Kun Kuang, Kelu Jiang +2
Adversarial training is one of the most effective approaches to improve model robustness against adversarial examples. However, previous works mainly focus on the overall robustnes…