Pith. sign in

REVIEW

AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Training

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.01106 v1 pith:ZTGTGYBX submitted 2023-09-03 cs.CV

AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Training

classification cs.CV
keywords adversarialdetectionobjecttrainingattacksmodelsmonocularapproach
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Monocular 3D object detection plays a pivotal role in the field of autonomous driving and numerous deep learning-based methods have made significant breakthroughs in this area. Despite the advancements in detection accuracy and efficiency, these models tend to fail when faced with such attacks, rendering them ineffective. Therefore, bolstering the adversarial robustness of 3D detection models has become a crucial issue that demands immediate attention and innovative solutions. To mitigate this issue, we propose a depth-aware robust adversarial training method for monocular 3D object detection, dubbed DART3D. Specifically, we first design an adversarial attack that iteratively degrades the 2D and 3D perception capabilities of 3D object detection models(IDP), serves as the foundation for our subsequent defense mechanism. In response to this attack, we propose an uncertainty-based residual learning method for adversarial training. Our adversarial training approach capitalizes on the inherent uncertainty, enabling the model to significantly improve its robustness against adversarial attacks. We conducted extensive experiments on the KITTI 3D datasets, demonstrating that DART3D surpasses direct adversarial training (the most popular approach) under attacks in 3D object detection $AP_{R40}$ of car category for the Easy, Moderate, and Hard settings, with improvements of 4.415%, 4.112%, and 3.195%, respectively.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.