arrow
返回

A Layer-Wise Extreme Network Compression for Super Resolution

delete2021-01-01
delete0
delete
OA
AI
J
Jiwon Hwang
A
A. F. M. Shahab Uddin
S
Sung‐Ho Bae *
DOI:10.1109/ACCESS.2021.3090404delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Deep neural networks (DNNs) for single image super-resolution (SISR) tend to have large model size and high computation complexity to achieve promising restoration performance. Unlike image classification, model compression for SISR has rarely been studied. In this paper, we found out that DNNs for image classification and SISR have often different characteristics in terms of layer importance. That is, contrary to the DNNs for image classification, the performance of SISR networks hardly decrease even if a few layers are eliminated during inference. This is due to the fact that they typically consist of a bunch of hierarchical and complex residual connections. Based on that key observation, we propose a layer-wise extreme network compression method for SISR. The proposed method consists of: i) reinforcement learning based joint framework for layer-wise quantization and pruning both of which are effectively incorporated into the search space; ii) a progressive preserve ratio scheduling that reflects importance in each layer more effectively, yielding much higher compression efficiency. Our comprehensive experiments show that the proposed method can effectively be applied to the existing SISR networks, thus extremely reducing the model size up to 97% (i.e., 1 bit per weight on average) with marginal performance degradation compared to the corresponding full-precision models.
Keyword:
Quantization (signal)
Image coding
Image reconstruction
Adaptation models
Degradation
Convolution
Task analysis
Single image super resolution
model compression
layer-wise
quantization
pruning
joint learning
reinforcement learning
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

K
kyung hee university
学者数:
2.3W
论文数: 2.2W
被引数: 234
引用论文

引用论文

Diagnosing Major Depressive Disorder I
err2006-03-01
err0
PREAI
errMark Zimmerman; Joseph B. McGlinchey; Diane Young; Iwona Chelminski
err分享
err收藏
Computational characterization of a-Si:H/c-Si interfaces
err2018-08-30
err0
PREAI
errPhilippe Czaja; Simone Giusepponi; Michele Gusso; Massimo Celino; Urs Aeberhard
err分享
err收藏
Calcium-modulating cyclophilin ligand regulates membrane trafficking of postsynaptic GABAA receptors
err2008-06-01
err0
errOAAI
errXu Yuan; Jun Yao; David Norris; David D. Tran; Richard J. Bram; Gong Chen; Bernhard Luscher
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
err分享
err收藏
学者 查看更多内容