R-TOSS: A Framework for Real-Time Object Detection using Semi-Structured Pruning

2023/03/03 by Balasubramaniam, Abhishek, Sunny, Febin P, Pasricha, Sudeep · 1 citation
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2303.02191

Abstract

Object detectors used in autonomous vehicles can have high memory and computational overheads. In this paper, we introduce a novel semi-structured pruning framework called R-TOSS that overcomes the shortcomings of state-of-the-art model pruning techniques. Experimental results on the JetsonTX2 show that R-TOSS has a compression rate of 4.4x on the YOLOv5 object detector with a 2.15x speedup in inference time and 57.01% decrease in energy usage. R-TOSS also enables 2.89x compression on RetinaNet with a 1.86x speedup in inference time and 56.31% decrease in energy usage. We also demonstrate significant improvements compared to various state-of-the-art pruning techniques.

Cited by

• A Novel Compression Framework for YOLOv8: Achieving Real-Time Aerial Object Detection on Edge Devices via Structured Pruning and Channel-Wise Distillation

Related

• Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search
• Optimizing Anchor-based Detectors for Autonomous Driving Scenes
• UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles
• YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles
• R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving