activity
20212024
most citedPhysics-informed Convolutional Neural Networks for Temperature Field Prediction of Heat Source Layout without Labeled Data

11 citations · 12 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2023

Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations

Jialiang Sun, Wen Yao, Tingsong Jiang +1

Deep neural networks have proven to be vulnerable to adversarial attacks in the form of adding specific perturbations on images to make wrong outputs. Designing stronger adversaria…

cs.CV20231 cited

RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World

Donghua Wang, Wen Yao, Tingsong Jiang +2

Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches…

cs.CV2023

A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications

Donghua Wang, Wen Yao, Tingsong Jiang +3

Wide deployment of deep neural networks (DNNs) based applications (e.g., style transfer, cartoonish), stimulating the requirement of copyright protection of such application's prod…

cs.CV2023

Efficient Search of Comprehensively Robust Neural Architectures via Multi-fidelity Evaluation

Jialiang Sun, Wen Yao, Tingsong Jiang +1

Neural architecture search (NAS) has emerged as one successful technique to find robust deep neural network (DNN) architectures. However, most existing robustness evaluations in NA…

cs.CV2023

Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical World

Chengyin Hu, Weiwen Shi, Tingsong Jiang +3

Infrared imaging systems have a vast array of potential applications in pedestrian detection and autonomous driving, and their safety performance is of great concern. However, few…

cs.CV2022

Contrastive Enhancement Using Latent Prototype for Few-Shot Segmentation

Xiaoyu Zhao, Xiaoqian Chen, Zhiqiang Gong +3

Few-shot segmentation enables the model to recognize unseen classes with few annotated examples. Most existing methods adopt prototype learning architecture, where support prototyp…