On the Robustness of 3D Object Detectors
In recent years, significant progress has been achieved for 3D object detection on point clouds thanks to the advances in 3D data collection and deep learning techniques. Nevertheless, 3D scenes exhibit a lot of variations and are prone to sensor inaccuracies as well as information loss during pre-processing. Thus, it is crucial to design techniques that are robust against these variations. This requires a detailed analysis and understanding of the effect of such variations. This work aims to analyze and benchmark popular point-based 3D object detectors against several data corruptions. To the best of our knowledge, we are the first to investigate the robustness of point-based 3D object detectors. To this end, we design and evaluate corruptions that involve data addition, reduction, and alteration. We further study the robustness of different modules against local and global variations. Our experimental results reveal several intriguing findings. For instance, we show that methods that integrate Transformers at a patch or object level lead to increased robustness, compared to using Transformers at the point level.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
On the Importance of Backbone to the Adversarial Robustness of Object Detectors
Object detection is a critical component of various security-sensitive applications, such as autonomous driving and video surveillance. However, existing object detectors are vulnerable to adversarial attacks, which pose…
Adversarial RobustnessAutonomous DrivingObjectobject-detection+2A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks
Recent years have witnessed significant advancements in deep learning-based 3D object detection, leading to its widespread adoption in numerous applications. As 3D object detectors become increasingly crucial for securit…
3D Object DetectionBenchmarkingObjectobject-detection+1COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts
Practical object detection application can lose its effectiveness on image inputs with natural distribution shifts. This problem leads the research community to pay more attention on the robustness of detectors under Out…
Autonomous DrivingObjectobject-detectionObject Detection+1LipSSD: Lipschitz-Constrained Single-Shot Detection for Adversarially Robust Object Detection
Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their applicability in real-world scenarios. Co…
Robust Object DetectionAdversarial RobustnessTowards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
The current approach for testing the robustness of object detectors suffers from serious deficiencies such as improper methods of performing out-of-distribution detection and using calibration metrics which do not consid…
Autonomous DrivingObjectobject-detectionObject Detection+2