Multi-Representation Adapter with Neural Architecture Search for Efficient Range-Doppler Radar Object Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918133634170880 |
|---|---|
| author | Lin, Zhiwei Zheng, Weicheng Wang, Yongtao |
| author_facet | Lin, Zhiwei Zheng, Weicheng Wang, Yongtao |
| contents | Detecting objects efficiently from radar sensors has recently become a popular trend due to their robustness against adverse lighting and weather conditions compared with cameras. This paper presents an efficient object detection model for Range-Doppler (RD) radar maps. Specifically, we first represent RD radar maps with multi-representation, i.e., heatmaps and grayscale images, to gather high-level object and fine-grained texture features. Then, we design an additional Adapter branch, an Exchanger Module with two modes, and a Primary-Auxiliary Fusion Module to effectively extract, exchange, and fuse features from the multi-representation inputs, respectively. Furthermore, we construct a supernet with various width and fusion operations in the Adapter branch for the proposed model and employ a One-Shot Neural Architecture Search method to further improve the model's efficiency while maintaining high performance. Experimental results demonstrate that our model obtains favorable accuracy and efficiency trade-off. Moreover, we achieve new state-of-the-art performance on RADDet and CARRADA datasets with mAP@50 of 71.9 and 57.1, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01280 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Representation Adapter with Neural Architecture Search for Efficient Range-Doppler Radar Object Detection Lin, Zhiwei Zheng, Weicheng Wang, Yongtao Computer Vision and Pattern Recognition Detecting objects efficiently from radar sensors has recently become a popular trend due to their robustness against adverse lighting and weather conditions compared with cameras. This paper presents an efficient object detection model for Range-Doppler (RD) radar maps. Specifically, we first represent RD radar maps with multi-representation, i.e., heatmaps and grayscale images, to gather high-level object and fine-grained texture features. Then, we design an additional Adapter branch, an Exchanger Module with two modes, and a Primary-Auxiliary Fusion Module to effectively extract, exchange, and fuse features from the multi-representation inputs, respectively. Furthermore, we construct a supernet with various width and fusion operations in the Adapter branch for the proposed model and employ a One-Shot Neural Architecture Search method to further improve the model's efficiency while maintaining high performance. Experimental results demonstrate that our model obtains favorable accuracy and efficiency trade-off. Moreover, we achieve new state-of-the-art performance on RADDet and CARRADA datasets with mAP@50 of 71.9 and 57.1, respectively. |
| title | Multi-Representation Adapter with Neural Architecture Search for Efficient Range-Doppler Radar Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.01280 |