Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks
원문 초록
Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant threats to system security. Traditional adversarial training methods, which require ground-truth labels, are not directly applicable to MDE models that lack ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) overlook the domain knowledge of MDE, resulting in suboptimal performance. In this work, we introduce a novel self-supervised adversarial training approach for MDE models, leveraging view synthesis without the need for ground-truth depth. We enhance adversarial robustness against real-world attacks by incorporating L_0-norm-bounded perturbation during training. We evaluate our method against supervised learning-based and contrastive learning-based approaches specifically designed for MDE. Our experiments with two representative MDE networks demonstrate improved robustness against various adversarial attacks, with minimal impact on benign performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Scale-Oriented Contrast
Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation
PhaseCam3D — Learning Phase Masks for Passive Single View Depth Estimation
MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training
ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory Forecasting
토론
이 논문과 연결된 포럼 글이 아직 없습니다.