YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs
Authors:
- 1 January 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1311-1321
Abstract
Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly, thus compromising the model accuracy. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods. Additionally, we propose a novel transfer learning backbone adoption inspired by the changing translational information flow across various tasks, designed to complement our feature interaction module and together improve both accuracy as well as execution speed on various edge GPU devices available in the market. For instance, YOLO-ReT with MobileNetV2×0.75 backbone runs real-time on Jetson Nano, and achieves 68.75 mAP on Pascal VOC and 34.91 mAP on COCO, beating its peers by 3.05 mAP and 0.91 mAP respectively, while executing faster by 3.05 FPS. Furthermore, introducing our multi-scale feature interaction module in YOLOv4-tiny and YOLOv4-tiny (3l) improves their performance to 41.5 and 48.1 mAP respectively on COCO, outperforming the original versions by 1.3 and 0.9 mAP.Keywords
All Related Versions
Funding Information
- Qatar National Research Fund
- National Research Foundation
This publication has 44 references indexed in Scilit:
- Path Aggregation Network for Instance Segmentation2018
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018
- Machine learning on FPGAs to face the IoT revolution2017
- Ball tracking in sports: a surveyArtificial Intelligence Review, 2017
- Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in VideoJournal of Computational Vision and Imaging Systems, 2017
- Feature Pyramid Networks for Object Detection2017
- SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving2017
- Deep Residual Learning for Image Recognition2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009