TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection
L. Cheng, S. Cao
IEEE Transactions on Radar Systems, 2025 , Vol. 3 , pp. 303-317
Abstract
TransRAD is a novel 3D radar object detection model that leverages the Retentive Vision Transformer (RMT) to learn features from radar Range-Azimuth-Doppler (RAD) data. The approach incorporates the Retentive Manhattan Self-Attention (MaSA) mechanism to align with spatial saliency characteristics of radar targets, and proposes Location-Aware NMS to mitigate duplicate bounding boxes in deep radar object detection.
Citation
L. Cheng, S. Cao. "TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection." IEEE Transactions on Radar Systems 3: 303-317, 2025. DOI: 10.1109/TRS.2025.3537604
Quick Links
Details
- Year
- 2025
- Published In
- IEEE Transactions on Radar Systems
- Volume
- 3
- Pages
- 303-317
- DOI
- 10.1109/TRS.2025.3537604