An Energy-Efficient FPGA-Based Deconvolutional Neural Networks Accelerator for Single Image Super-Resolution
- 20 December 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 30 (1) , 281-295
Abstract
Convolutional neural networks (CNNs) demonstrate excellent performance in various computer vision applications. In recent years, FPGA-based CNN accelerators have been proposed for optimizing performance and power efficiency. Most accelerators are designed for object detection and recognition algorithms that are performed on low-resolution (LR) images. However, real-time image super-resolution (SR) cannot be implemented on a typical accelerator because of the long execution cycles required to generate high-resolution (HR) images, such as those used in ultra-high-definition (UHD) systems. In this paper, we propose a novel CNN accelerator with efficient parallelization methods for SR applications. First, we propose a new methodology for optimizing the deconvolutional neural networks (DCNNs) used for increasing feature maps. Secondly, we propose a novel method to optimize CNN dataflow so that the SR algorithm can be driven at low power in display applications. Finally, we quantize and compress a DCNN-based SR algorithm into an optimal model for efficient inference using on-chip memory. We present an energyefficient architecture for SR and validate our architecture on a mobile panel with quad-high-definition (QHD) resolution. Our experimental results show that, with the same hardware resources, the proposed DCNN accelerator achieves a throughput up to 108 times greater than that of a conventional DCNN accelerator. In addition, our SR system achieves an energy efficiency of 144.9 GOPS/W, 293.0 GOPS/W, and 500.2 GOPS/W at SR scale factors of 2, 3, and 4, respectively. Furthermore, we demonstrate that our system can restore HR images to a high quality while greatly reducing the data bit-width and the number of parameters compared to conventional SR algorithms.Keywords
All Related Versions
Funding Information
- MSIT (Ministry of Science and ICT), Korea
- ITRC (IITP-2018-0-01421)
- National Research Foundation of Korea
- Korea government (2018R1D1 A1B07048421)
This publication has 29 references indexed in Scilit:
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- Text-Attentional Convolutional Neural Network for Scene Text DetectionIEEE Transactions on Image Processing, 2016
- Going Deeper with Embedded FPGA Platform for Convolutional Neural Network2016
- Design space exploration of FPGA-based Deep Convolutional Neural Networks2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- DianNaoACM SIGPLAN Notices, 2014
- RooflineCommunications of the ACM, 2009