Paper Info
Title
ATMFN: Adaptive-threshold-based Multi-model Fusion Network for Compressed Face Hallucination
Abstract
Although tremendous strides have been recently made in face hallucination, exiting methods based on a single deep learning framework can hardly satisfactorily provide fine facial features from tiny faces under complex degradation. This article advocates an adaptive-threshold-based multi-model fusion network (ATMFN) for compressed face hallucination, which unifies different deep learning models to take advantages of their respective learning merits. First of all, we construct CNN-, GAN- and RNN-based underlying super-resolvers to produce candidate SR results. Further, the attention subnetwork is proposed to learn the individual fusion weight matrices capturing the most informative components of the candidate SR faces. Particularly, the hyper-parameters of the fusion matrices and the underlying networks are optimized together in an end-to-end manner to drive them for collaborative learning. Finally, a threshold-based fusion and reconstruction module is employed to exploit the candidates’ complementarity and thus generate high-quality face images. Extensive experiments on benchmark face datasets and real-world samples show that our model outperforms the state-of-the-art SR methods in terms of quantitative indicators and visual effects. The code and configurations are released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/kuihua/ATMFN</uri> .
Year
DOI
Venue
2020
10.1109/TMM.2019.2960586
IEEE Transactions on Multimedia
Keywords
DocType
Volume
Face,Image resolution,Image reconstruction,Deep learning,Adaptation models,Task analysis,Gallium nitride
Journal
22
Issue
ISSN
Citations 
10
1520-9210
5
PageRank 
References 
Authors
0.41
0
6
Name
Order
Citations
PageRank
Kui Jiang19417.91
Zhongyuan Wang222725.14
Peng Yi33612.92
Guangcheng Wang4245.05
Ke Gu5132177.21
Junjun Jiang6113874.49