PEFT-DML: Parameter-Efficient Fine-Tuning Deep Metric Learning for Robust Multi-Modal 3D Object Detection in Autonomous Driving
This addresses reliability issues in autonomous driving systems when sensors fail or conditions vary, representing a strong domain-specific improvement.
This study tackled robust multi-modal 3D object detection in autonomous driving under sensor dropout and diverse conditions, introducing PEFT-DML which achieved superior accuracy on nuScenes benchmarks with significant training efficiency gains.
This study introduces PEFT-DML, a parameter-efficient deep metric learning framework for robust multi-modal 3D object detection in autonomous driving. Unlike conventional models that assume fixed sensor availability, PEFT-DML maps diverse modalities (LiDAR, radar, camera, IMU, GNSS) into a shared latent space, enabling reliable detection even under sensor dropout or unseen modality class combinations. By integrating Low-Rank Adaptation (LoRA) and adapter layers, PEFT-DML achieves significant training efficiency while enhancing robustness to fast motion, weather variability, and domain shifts. Experiments on benchmarks nuScenes demonstrate superior accuracy.