Marvin Klingner — accepted AI-conference papers

2023

X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection

Marvin Klingner, Shubhankar Borse, Varun Ravi Kumar, Behnaz Rezaei, Venkatraman Narayanan, Senthil Yogamani +1

CVPR 2023poster

Recent advances in 3D object detection (3DOD) have obtained remarkably strong results for LiDAR-based models. In contrast, surround-view 3DOD models based on multiple camera images underperform due to the necessary view transformation of features from perspective view (PV) to a 3D world representati…

Cited by 35 Source ↗PDF ↗Scholar ↗

2022

Detecting Adversarial Perturbations in Multi-Task Perception

Marvin Klingner, Varun Ravi Kumar, Senthil Yogamani, Andreas Bär, Tim Fingscheidt

IROS 2022poster

While deep neural networks (DNNs) achieve impressive performance on environment perception tasks, their sensitivity to adversarial perturbations limits their use in practical applications. In this paper, we (i) propose a novel adversarial perturbation detection scheme based on multi-task perception…

Cited by 23 Source ↗code ↗Scholar ↗

2020

Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

Marvin Klingner, Jan-Aike Termhlen, Jonas Mikolajczyk, Tim Fingscheidt

ECCV 2020poster

Self-supervised monocular depth estimation presents a powerful method to obtain 3D scene information from single camera images, which is trainable on arbitrary image sequences without requiring depth labels, e.g., from a LiDAR sensor. In this work we present a new self-supervised semantically-guided…

Cited by 394 Source ↗PDF ↗code ↗Scholar ↗