Black-box Adversarial Attacks on Monocular Depth Estimation Using Evolutionary Multi-objective Optimization

no code implementations • 29 Dec 2020 • Renya Daimo, Satoshi Ono, Takahiro Suzuki

This paper proposes an adversarial attack method to deep neural networks (DNNs) for monocular depth estimation, i. e., estimating the depth from a single image.

Adversarial Attack Image Classification +1