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.
@article{arxiv.2512.00060,
title = {PEFT-DML: Parameter-Efficient Fine-Tuning Deep Metric Learning for Robust Multi-Modal 3D Object Detection in Autonomous Driving},
author = {Abdolazim Rezaei and Mehdi Sookhak},
journal= {arXiv preprint arXiv:2512.00060},
year = {2025}
}