PEFT-DML: Parameter-Efficient Fine-Tuning Deep Metric Learning for Robust Multi-Modal 3D Object Detection in Autonomous Driving
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911293831643136 |
|---|---|
| author | Rezaei, Abdolazim Sookhak, Mehdi |
| author_facet | Rezaei, Abdolazim Sookhak, Mehdi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_00060 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PEFT-DML: Parameter-Efficient Fine-Tuning Deep Metric Learning for Robust Multi-Modal 3D Object Detection in Autonomous Driving Rezaei, Abdolazim Sookhak, Mehdi Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | PEFT-DML: Parameter-Efficient Fine-Tuning Deep Metric Learning for Robust Multi-Modal 3D Object Detection in Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.00060 |