Skip to yearly menu bar Skip to main content


Detection as Regression: Certified Object Detection with Median Smoothing

Ping-yeh Chiang · Michael Curry · Ahmed Abdelkader · Aounon Kumar · John Dickerson · Tom Goldstein

Poster Session 5 #1579

Keywords: [ Algorithms ] [ Unsupervised Learning ] [ Perception ] [ Applications -> Robotics; Neuroscience and Cognitive Science ]

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.

Chat is not available.