Full-Distance Evasion of Pedestrian Detectors in the Physical World
Zhi Cheng, Zhanhao Hu, Yuqiu Liu, Jianmin Li, Hang Su, Xiaolin Hu
Abstract
Many studies have proposed attack methods to generate adversarial patterns for evading pedestrian detection, alarming the computer vision community about the need for more attention to the robustness of detectors. However, adversarial patterns optimized by these methods commonly have limited performance at medium to long distances in the physical world. To overcome this limitation, we identify two main challenges. First, in existing methods, there is commonly an appearance gap between simulated distant adversarial patterns and their physical world counterparts, leading to incorrect optimization. Second, there exists a conflict between adversarial losses at different distances, which causes difficulties in optimization. To overcome these challenges, we introduce a Full Distance Attack (FDA) method. Our physical world experiments demonstrate the effectiveness of our FDA patterns across various detection models like YOLOv5, Deformable-DETR, and Mask RCNN. Codes available at https://github.com/zhicheng2T0/Full-Distance-Attack.git
BibTeX
@inproceedings{
cheng2024fulldistance,
title={Full-Distance Evasion of Pedestrian Detectors in the Physical World},
author={Zhi Cheng and Zhanhao Hu and Yuqiu Liu and Jianmin Li and Hang Su and Xiaolin Hu},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=lWYwZklSvg}
}