Title:
PRUNING AND QUANTIZATION COMPRESSION METHOD AND SYSTEM FOR SUPER-RESOLUTION NETWORK, AND MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/262660
Kind Code:
A1
Abstract:
Disclosed are a pruning and quantization compression method and system for a super-resolution network, and a medium. The method comprises the following steps: obtaining an original super-resolution model; performing closed-loop dual reconstruction training on the original super-resolution model; performing closed-loop dual pruning on the obtained and trained original super-resolution model to obtain a pruning model; performing parameter optimization on the pruning model to obtain a lightweight super-resolution pruning model; and performing quantization compression on the super-resolution pruning model to obtain a compressed super-resolution model. According to the present invention, by using a dual reconstruction loss function, in a channel pruning process, the solution space for a super-resolution task is reduced, thus the importance of each channel in an original model on super-resolution reconstruction can be more accurately evaluated, and a more compact compression model is obtained by reserving such channels. Moreover, the present invention can be widely applied to the technical field of computer vision.
More Like This:
Inventors:
TAN MINGKUI (CN)
GUO YONG (CN)
DENG ZESHUAI (CN)
GUO YONG (CN)
DENG ZESHUAI (CN)
Application Number:
PCT/CN2022/098207
Publication Date:
December 22, 2022
Filing Date:
June 10, 2022
Export Citation:
Assignee:
UNIV SOUTH CHINA TECH (CN)
International Classes:
G06T3/40
Foreign References:
| CN113379604A | 2021-09-10 | |||
| CN111652366A | 2020-09-11 | |||
| CN112580381A | 2021-03-30 | |||
| CN110009565A | 2019-07-12 | |||
| CN112861996A | 2021-05-28 | |||
| CN110222820A | 2019-09-10 | |||
| CN112329922A | 2021-02-05 | |||
| US20210089922A1 | 2021-03-25 |
Other References:
GUO YONG; CHEN JIAN; WANG JINGDONG; CHEN QI; CAO JIEZHANG; DENG ZESHUAI; XU YANWU; TAN MINGKUI: "Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution", 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), IEEE, 13 June 2020 (2020-06-13), pages 5406 - 5415, XP033803531, DOI: 10.1109/CVPR42600.2020.00545
JING LIU; BOHAN ZHUANG; ZHUANGWEI ZHUANG; YONG GUO; JUNZHOU HUANG; JINHUI ZHU; MINGKUI TAN: "Discrimination-aware Network Pruning for Deep Model Compression", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 4 January 2020 (2020-01-04), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081572196
ZHUANGWEI ZHUANG; MINGKUI TAN; BOHAN ZHUANG; JING LIU; YONG GUO; QINGYAO WU; JUNZHOU HUANG; JINHUI ZHU: "Discrimination-aware Channel Pruning for Deep Neural Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 28 October 2018 (2018-10-28), 201 Olin Library Cornell University Ithaca, NY 14853 , XP080925940
JING LIU; BOHAN ZHUANG; ZHUANGWEI ZHUANG; YONG GUO; JUNZHOU HUANG; JINHUI ZHU; MINGKUI TAN: "Discrimination-aware Network Pruning for Deep Model Compression", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 4 January 2020 (2020-01-04), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081572196
ZHUANGWEI ZHUANG; MINGKUI TAN; BOHAN ZHUANG; JING LIU; YONG GUO; QINGYAO WU; JUNZHOU HUANG; JINHUI ZHU: "Discrimination-aware Channel Pruning for Deep Neural Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 28 October 2018 (2018-10-28), 201 Olin Library Cornell University Ithaca, NY 14853 , XP080925940
Attorney, Agent or Firm:
JIAQUAN IP LAW (CN)
Download PDF: