Adversarial Patch Attacks on Monocular Depth Estimation Networks

Adversarial Patch Attacks on Monocular Depth Estimation Networks

Thanks to the excellent learning capability of deep convolutional neural networks (CNN), monocular depth estimation using CNNs has achieved great success in recent years. However, depth estimation from a monocular image alone is essentially an ill-posed problem, and thus, it seems that this approach...

Full description

Bibliographic Details
Main Authors: Koichiro Yamanaka, Ryutaroh Matsumoto, Keita Takahashi, Toshiaki Fujii
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Adversarial attack
monocular depth estimation
CNN
Online Access:https://ieeexplore.ieee.org/document/9207958/

Internet

https://ieeexplore.ieee.org/document/9207958/

Similar Items