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

03/03/2023

∙

by   Abhishek Balasubramaniam, et al.

∙

0

∙

share

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 usage. R-TOSS also enables 2.89x compression on RetinaNet with a 1.86x speedup in inference time and 56.31 significant improvements compared to various state-of-the-art pruning techniques.