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

被引：5

作者：

Balasubramaniam, Abhishek ^{[1
]}

Sunny, Febin ^{[1
]}

Pasricha, Sudeep ^{[1
]}

机构：

[1] Colorado State Univ, Dept Elect & Comp Engn, Ft Collins, CO 80523 USA

来源：

2023 60TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC | 2023年

关键词：

pruning; object detection; YOLOv5; RetinaNet; Jetson TX2; model compression; computer vision;

D O I：

10.1109/DAC56929.2023.10247917

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 platform 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.

引用

页数：6

共 50 条

[41] A Real-time Object Detection Framework for Aerial Imagery Using Deep Neural Networks and Synthetic Training Images [J].

Narayanan, Priya ;

Borel-Donohue, Christoph ;

Lee, Hyungtae ;

Kwon, Heesung ;

Rao, Raghuveer .

SIGNAL PROCESSING, SENSOR/INFORMATION FUSION, AND TARGET RECOGNITION XXVII, 2018, 10646

[42] Comparison of CW Radar Systems for Radar Applications using Object Detection and Real-Time Tracking [J].

Melgoza, Cesar Martinez ;

George, Kiran ;

Miho, Jake .

2022 IEEE 13TH ANNUAL UBIQUITOUS COMPUTING, ELECTRONICS & MOBILE COMMUNICATION CONFERENCE (UEMCON), 2022, :342-346

[43] Hardware-Software Partitioning for Real-Time Object Detection Using Dynamic Parameter Optimization [J].

Zaharia, Corneliu ;

Popescu, Vlad ;

Sandu, Florin .

SENSORS, 2023, 23 (10)

[44] UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles [J].

Balasubramaniam, Abhishek ;

Sunny, Febin P. ;

Pasricha, Sudeep .

2025 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE, DATE, 2025,

[45] A Wearable Assistive Device for Blind Pedestrians Using Real-Time Object Detection and Tactile Presentation [J].

Shen, Junjie ;

Chen, Yiwen ;

Sawada, Hideyuki .

SENSORS, 2022, 22 (12)

[46] Robust object detection with real-time fusion of multiview foreground silhouettes [J].

Xu, Ming ;

Ren, Jie ;

Chen, Dongyong ;

Smith, Jeremy S. ;

Liu, Zhechi ;

Jia, Tianyuan .

OPTICAL ENGINEERING, 2012, 51 (04)

[47] Deep Learning Based, Real-Time Object Detection for Autonomous Driving [J].

Akyol, Gamze ;

Kantarci, Alperen ;

Celik, Ali Eren ;

Ak, Abdullah Cihan .

2020 28TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2020,

[48] Real-time Object Detection for Visually Impaired with Optimal Combination of Scores [J].

Nijhawan, Siddharth Sagar ;

Kumar, Aditi ;

Bhardwaj, Shubham ;

Nijhawan, Geeta .

PROCEEDINGS OF THE 2019 6TH INTERNATIONAL CONFERENCE ON COMPUTING FOR SUSTAINABLE GLOBAL DEVELOPMENT (INDIACOM), 2019, :307-311

[49] Real-Time Abnormal Object Detection for Video Surveillance in Smart Cities [J].

Ingle, Palash Yuvraj ;

Kim, Young-Gab .

SENSORS, 2022, 22 (10)

[50] Evaluating Pruned Object Detection Networks for Real-Time Robot Vision [J].

O'Keeffe, Simon ;

Villing, Rudi .

2018 IEEE INTERNATIONAL CONFERENCE ON AUTONOMOUS ROBOT SYSTEMS AND COMPETITIONS (ICARSC), 2018, :91-96

← 1 2 3 4 5 →