Fooling human detectors via robust and visually natural adversarial patches
Authors:
- Dawei ZhouDZDawei Zhou
- Hongbin QuHQHongbin Qu
- Nannan WangNWNannan Wang
- Chunlei PengCPChunlei Peng
- Zhuoqi MaZMZhuoqi Ma
- Xi YangXYXi Yang
- Xinbo GaoXGXinbo Gao
- 17 November 2024
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 616
Abstract
No abstract availableKeywords
This publication has 19 references indexed in Scilit:
- Universal Physical Camouflage Attacks on Object Detectors2020
- Robust Physical-World Attacks on Deep Learning Visual Classification2018
- YOLO9000: Better, Faster, Stronger2017
- Universal Adversarial Perturbations2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Image Style Transfer Using Convolutional Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Fully convolutional networks for semantic segmentation2015
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification2014
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis2014