Back to Search
Start Over
SA-YOLOv3: An Efficient and Accurate Object Detector Using Self-Attention Mechanism for Autonomous Driving.
- Source :
- IEEE Transactions on Intelligent Transportation Systems; May2022, Vol. 23 Issue 5, p4099-4110, 12p
- Publication Year :
- 2022
-
Abstract
- Object detection is becoming increasingly significant for autonomous-driving system. However, poor accuracy or low inference performance limits current object detectors in applying to autonomous driving. In this work, a fast and accurate object detector termed as SA-YOLOv3, is proposed by introducing dilated convolution and self-attention module (SAM) into the architecture of YOLOv3. Furthermore, loss function based on GIoU and focal loss is reconstructed to further optimize detection performance. With an input size of $512\times 512$ , our proposed SA-YOLOv3 improves YOLOv3 by 2.58 mAP and 2.63 mAP on KITTI and BDD100K benchmarks, with real-time inference (more than 40 FPS). When compared with other state-of-the-art detectors, it reports better trade-off in terms of detection accuracy and speed, indicating the suitability for autonomous-driving application. To our best knowledge, it is the first method that incorporates YOLOv3 with attention mechanism, and we expect this work would guide for autonomous-driving research in the future. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 15249050
- Volume :
- 23
- Issue :
- 5
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Intelligent Transportation Systems
- Publication Type :
- Academic Journal
- Accession number :
- 156717976
- Full Text :
- https://doi.org/10.1109/TITS.2020.3041278