カメラ運動摂動に対する認証ロバスト性のためのピクセル単位スムージング
Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
3Dカメラ運動空間での高コストなサンプリングを避け、2Dピクセル空間でのスムージング分布を用いることで、カメラ運動摂動に対するロバスト性認証を効率化するフレームワークを提案した。
著者: Hanjiang Hu, Zuxin Liu, Linyi Li, Jiacheng Zhu, Ding Zhao
分類: cs.LG, cs.CV, cs.RO
原文アブストラクト
Deep learning-based visual perception models lack robustness when faced with camera motion perturbations in practice. The current certification process for assessing robustness is costly and time-consuming due to the extensive number of image projections required for Monte Carlo sampling in the 3D camera motion space. To address these challenges, we present a novel, efficient, and practical framework for certifying the robustness of 3D-2D projective transformations against camera motion perturbations. Our approach leverages a smoothing distribution over the 2D pixel space instead of in the 3D physical space, eliminating the need for costly camera motion sampling and significantly enhancing the efficiency of robustness certifications. With the pixel-wise smoothed classifier, we are able to fully upper bound the projection errors using a technique of uniform partitioning in camera motion space. Additionally, we extend our certification framework to a more general scenario where only a single-frame point cloud is required in the projection oracle. Through extensive experimentation, we validate the trade-off between effectiveness and efficiency enabled by our proposed method. Remarkably, our approach achieves approximately 80% certified accuracy while utilizing only 30% of the projected image frames. The code is available at https://github.com/HanjiangHu/pixel-wise-smoothing.
