|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM375759638 |
| 003 |
DE-627 |
| 005 |
20240807233106.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240802s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2024.3434426
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1494.xml
|
| 035 |
|
|
|a (DE-627)NLM375759638
|
| 035 |
|
|
|a (NLM)39088501
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Sun, Lingchen
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Perception-Distortion Balanced Super-Resolution
|b A Multi-Objective Optimization Perspective
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 07.08.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a High perceptual quality and low distortion degree are two important goals in image restoration tasks such as super-resolution (SR). Most of the existing SR methods aim to achieve these goals by minimizing the corresponding yet conflicting losses, such as the l1 loss and the adversarial loss. Unfortunately, the commonly used gradient-based optimizers, such as Adam, are hard to balance these objectives due to the opposite gradient decent directions of the contradictory losses. In this paper, we formulate the perception-distortion trade-off in SR as a multi-objective optimization problem and develop a new optimizer by integrating the gradient-free evolutionary algorithm (EA) with gradient-based Adam, where EA and Adam focus on the divergence and convergence of the optimization directions respectively. As a result, a population of optimal models with different perception-distortion preferences is obtained. We then design a fusion network to merge these models into a single stronger one for an effective perception-distortion trade-off. Experiments demonstrate that with the same backbone network, the perception-distortion balanced SR model trained by our method can achieve better perceptual quality than its competitors while attaining better reconstruction fidelity. Codes and models can be found at https://github.com/csslc/EA-Adam
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Liang, Jie
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Shuaizheng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yong, Hongwei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Lei
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 33(2024) vom: 01., Seite 4444-4458
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:33
|g year:2024
|g day:01
|g pages:4444-4458
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2024.3434426
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 33
|j 2024
|b 01
|h 4444-4458
|