Litcius/Paper detail

Accelerating Tiny YOLOv3 using FPGA-Based Hardware/Software Co-Design

Afzal Ahmad, Muhammad Adeel Pasha, Ghulam Jilani Raza

202044 citationsDOI

Abstract

Convolutional Neural Networks (CNNs) are influencing major breakthroughs in computer vision by achieving unprecedented accuracy on tasks such as image classification, object detection, landmark detection and semantic segmentation. Owing to high computational complexity of most modern CNN architectures, graphical processing units (GPUs) are being utilized to achieve real-time performance albeit at a high energy cost. Consequently, Field Programmable Gate Arrays (FPGAs) based hardware accelerators are also making their way as they demonstrate GPU-like performance with significantly lower energy consumption that is well-suited for embedded vision applications. In this paper, we employ Hardware/Software Co-Design approach to accelerate Tiny YOLOv3 - an efficient CNN architecture for object detection - by designing a hardware accelerator for convolution, the most complex operation involved in the CNNs. Experimental results show significant performance gains, in the range of 3.9× to 21.3×, over previous implementations of efficient object detection algorithms.

Topics & Concepts

Field-programmable gate arrayComputer scienceObject detectionConvolutional neural networkSoftwareHardware accelerationConvolution (computer science)SegmentationComputer architectureArtificial intelligenceReconfigurable computingEmbedded systemComputer hardwareArtificial neural networkProgramming languageAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesCCD and CMOS Imaging Sensors
Accelerating Tiny YOLOv3 using FPGA-Based Hardware/Software Co-Design | Litcius