Deep Compression on Convolutional Neural Network for Artistic Style Transfer

2017 ◽  
pp. 157-166 ◽  
Author(s):  
Jian Hu ◽  
Kun He ◽  
John E. Hopcroft ◽  
Yaren Zhang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer ◽  
Artistic Style

A Study on the Convolutional Neural Algorithm of Image Style Transfer

2019 ◽  
Vol 33 (05) ◽  
pp. 1954020 ◽  
Author(s):  
Fu Wen Yang ◽  
Hwei Jen Lin ◽  
Shwu-Huey Yen ◽  
Chun-Hui Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Computational Efficiency ◽  
Back Propagation ◽  
Deep Convolutional Neural Networks ◽  
Propagation Process ◽  
Energy Functions ◽  
Style Transfer ◽  
Artistic Style

Recently, deep convolutional neural networks have resulted in noticeable improvements in image classification and have been used to transfer artistic style of images. Gatys et al. proposed the use of a learned Convolutional Neural Network (CNN) architecture VGG to transfer image style, but problems occur during the back propagation process because there is a heavy computational load. This paper solves these problems, including the simplification of the computation of chains of derivatives, accelerating the computation of adjustments, and efficiently choosing weights for different energy functions. The experimental results show that the proposed solutions improve the computational efficiency and render the adjustment of weights for energy functions easier.

Applicability of Convolutional Neural Network Artistic Style Transfer Algorithms

2021 ◽  
pp. 61-81
Author(s):  
Penousal Machado ◽  
Juan Romero ◽  
Gary Greenfield
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer ◽  
Artistic Style

The contour image style-transfer-based convolutional neural network

2019 ◽  
Author(s):  
Nan Deng ◽  
Jing Li ◽  
Xingce Wang ◽  
Zhongke Wu ◽  
yan Fu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer

scholarly journals Rapid Local Image Style Transfer Method Based on Residual Convolutional Neural Network

2021 ◽  
Vol 33 (4) ◽  
pp. 1343
Author(s):  
Liming Huang ◽  
Ping Wang ◽  
Cheng-Fu Yang ◽  
Hsien-Wei Tseng
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer ◽  
Transfer Method ◽  
Local Image

scholarly journals An Image Style Transfer Network Using Multilevel Noise Encoding and Its Application in Coverless Steganography

Symmetry ◽  
2019 ◽  
Vol 11 (9) ◽  
pp. 1152
Author(s):  
Shanqing Zhang ◽  
Shengqi Su ◽  
Li Li ◽  
Qili Zhou ◽  
Jianfeng Lu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Color Image ◽  
Image Data ◽  
Cover Image ◽  
Stego Image ◽  
Style Transfer ◽  
Secret Information ◽  
Residual Learning ◽  
Short Period

Most of the existing image steganographic approaches embed the secret information imperceptibly into a cover image by slightly modifying its content. However, the modification traces will cause some distortion in the stego-image, especially when embedding color image data that usually contain thousands of bits, which makes successful steganalysis possible. A coverless steganographic approach without any modification for transmitting secret color image is proposed. We propose a diversity image style transfer network using multilevel noise encoding. The network consists of a generator and a loss network. A multilevel noise to encode matching the subsequent convolutional neural network scale is used in the generator. The diversity loss is increased in the loss network so that the network can generate diverse image style transfer results. Residual learning is introduced so that the training speed of network is significantly improved. Experiments show that the network can generate stable results with uniform texture distribution in a short period of time. These image style transfer results can be integrated into our coverless steganography scheme. The performance of our steganography scheme is good in steganographic capacity, anti-steganalysis, security, and robustness.

Controlling Stroke Size in Fast Style Transfer with Recurrent Convolutional Neural Network

2018 ◽  
Vol 37 (7) ◽  
pp. 97-107 ◽  
Author(s):  
Lingchen Yang ◽  
Lumin Yang ◽  
Mingbo Zhao ◽  
Youyi Zheng
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer

scholarly journals Convolutional Neural Network Style Transfer Towards Chinese Paintings

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 163719-163728
Author(s):  
Jiachuan Sheng ◽  
Caifeng Song ◽  
Jun Wang ◽  
Yahong Han
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Style Transfer

scholarly journals Design of a Human Evaluator Model for the Ride Comfort of Vehicle on a Speed Bump Using a Neural Artistic Style Extraction

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5407
Author(s):  
Donggyun Kim ◽  
MyeonGyu Jeong ◽  
ByungGuk Bae ◽  
Changsun Ahn
Keyword(s):  
Neural Network ◽  
Ride Comfort ◽  
Subjective Evaluation ◽  
Numerical Representation ◽  
Correlation Model ◽  
Subjective Ratings ◽  
Style Transfer ◽  
Artistic Style ◽  
Correlation Models ◽  
Objective Metrics

The subjective evaluation of vehicle ride comfort is costly and time-consuming but is crucial for vehicle development. To reduce the cost and time, the objectification of subjective evaluation has been widely studied, and most of the approaches use a regression model between objective metrics and subjective ratings. However, the accuracy of these approaches is highly dependent on the selection of the objective metrics. In most of the methods, it is not clear that the selected metrics are sufficiently significant or whether all significant metrics are included in the selection. This paper presents a method to build a correlation model between measurements and subjective evaluations without using predefined features or objective metrics. A numerical representation of ride comfort was extracted from raw signals based on the idea of the artistic style transfer method. The correlation model was designed based on the extracted numerical representation and subjective ratings. The model has a much better accuracy than any other correlation models in the literature. This better accuracy is contributed to not only by using a neural network, but also by the extraction of the numerical representation of ride comfort using a pre-trained neural network.

Sign in / Sign up

Export Citation Format

Share Document