CNN-based Super-Resolution (SR), the most representative of low-level vision task, is a promising solution to improve users' QoS on IoT devices that suffer from limited network bandwidth and storage capacity by effectively enhancing image/video resolution. Although prior accelerators to embed CNN show tremendous performance and energy efficiency, they are not suitable for SR tasks regarding off-chip memory accesses. In this work, we present eSRCNN, a framework that enables performing energy-efficient SR tasks on diverse embedded CNN accelerators by decreasing off-chip memory accesses. To reduce off-chip memory accesses, our framework consists of three steps: a network reformation using a cross-layer weight scaling, a precision minimization with priority-based quantization, and an activation map compression exploiting a data locality. As a result, the energy consumption of off-chip memory accesses is reduced up to 71.89% with less than 3.52% area overhead.
|Title of host publication||2019 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2019 - Digest of Technical Papers|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|State||Published - Nov 2019|
|Event||38th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2019 - Westin Westminster, United States|
Duration: 4 Nov 2019 → 7 Nov 2019
|Name||IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD|
|Conference||38th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2019|
|Period||4/11/19 → 7/11/19|
Bibliographical noteFunding Information:
This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (NO. 2017R1A2B2009380).
© 2019 IEEE.
- Activation Map Compression
- Convolutional Neural Network
- Network Reformation