Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 

Saved Queries

Sign in to use this feature.

Search Filter Reset All

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
Add Subjects Reset
Select Subjects

Journals

remove_circle_outline
Add Journals Reset
Select Journals

Article Types

remove_circle_outline
Add Article Types Reset
Select Article Types

Countries / Regions

remove_circle_outline
Add Countries / Regions Reset
Select Countries / Regions
Update Search
share announcement

Search Results (2)

Search Parameters:
Keywords = generative adverserial networks

Order results
Result details
Results per page
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
14 pages, 510 KiB  
Article
Knowledge Distillation for Image Signal Processing Using Only the Generator Portion of a GAN
by Youngjun Heo and Sunggu Lee
Electronics 2022, 11(22), 3815; https://doi.org/10.3390/electronics11223815 - 20 Nov 2022
Viewed by 2413
Abstract
Knowledge distillation, in which the parameter values learned in a large teacher network are transferred to a smaller student network, is a popular and effective network compression method. Recently, researchers have proposed methods to improve the performance of a student network by using [...] Read more.
Knowledge distillation, in which the parameter values learned in a large teacher network are transferred to a smaller student network, is a popular and effective network compression method. Recently, researchers have proposed methods to improve the performance of a student network by using a Generative Adverserial Network (GAN). However, because a GAN is an architecture that is ideally used to create realistic synthetic images, a pure GAN architecture may not be ideally suited for knowledge distillation. In knowledge distillation for image signal processing, synthetic images do not need to be realistic, but instead should include features that help the training of the student network. In the proposed Generative Image Processing (GIP) method, this is accomplished by using only the generator portion of a GAN and utilizing special techniques to capture the distinguishing feature capability of the teacher network. Experimental results show that the GIP method outperforms knowledge distillation using GANs as well as training using only knowledge distillation. Full article
(This article belongs to the Special Issue Feature Papers in Circuit and Signal Processing)
►▼ Show Figures

Figure 1

16 pages, 7384 KiB  
Article
Semi-Supervised FaceGAN for Face-Age Progression and Regression with Synthesized Paired Images
by Quang T. M. Pham, Janghoon Yang and Jitae Shin
Electronics 2020, 9(4), 603; https://doi.org/10.3390/electronics9040603 - 1 Apr 2020
Cited by 11 | Viewed by 7541
Abstract
The performance of existing face age progression or regression methods is often limited by the lack of sufficient data to train the model. To deal with this problem, we introduce a novel framework that exploits synthesized images to improve the performance. A conditional [...] Read more.
The performance of existing face age progression or regression methods is often limited by the lack of sufficient data to train the model. To deal with this problem, we introduce a novel framework that exploits synthesized images to improve the performance. A conditional generative adversarial network (GAN) is first developed to generate facial images with targeted ages. The semi-supervised GAN, called SS-FaceGAN, is proposed. This approach considers synthesized images with a target age and the face images from the real data so that age and identity features can be explicitly utilized in the objective function of the network. We analyze the performance of our method over previous studies qualitatively and quantitatively. The experimental results show that the SS-FaceGAN model can produce realistic human faces in terms of both identity preservation and age preservation with the quantitative results of a decent face detection rate of 97% and similarity score of 0.30 on average. Full article
(This article belongs to the Section Artificial Intelligence)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying article 1-50 on page 1 of 1.
Back to TopTop