Detection as Regression: Certified Object Detection with Median Smoothing
Abstract
Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image classifiers, a direct extension to object detection is very expensive. This work is motivated by recent progress on certified classification by randomized smoothing. We start by presenting a reduction from object detection to a regression problem. Then, to enable certified regression, where standard mean smoothing fails, we propose median smoothing, which is of independent interest. We obtain the first model-agnostic, training-free, and certified defense for object detection against $\ell_2$-bounded attacks.
Cite
Text
Chiang et al. "Detection as Regression: Certified Object Detection with Median Smoothing." Neural Information Processing Systems, 2020.Markdown
[Chiang et al. "Detection as Regression: Certified Object Detection with Median Smoothing." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/chiang2020neurips-detection/)BibTeX
@inproceedings{chiang2020neurips-detection,
title = {{Detection as Regression: Certified Object Detection with Median Smoothing}},
author = {Chiang, Ping-yeh and Curry, Michael and Abdelkader, Ahmed and Kumar, Aounon and Dickerson, John and Goldstein, Tom},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/chiang2020neurips-detection/}
}