Image Style Transfer with Multi-target Loss for loT Applications
| Title | Image Style Transfer with Multi-target Loss for loT Applications |
| Publication Type | Conference Paper |
| Year of Publication | 2018 |
| Authors | Wang, C., He, M. |
| Conference Name | 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks (I-SPAN) |
| Date Published | oct |
| Keywords | arbitrary images, artistic images, Computer vision, content style, context image, feature extraction, feature map, Filter banks, fundamental problem, gradient methods, Image reconstruction, image style transfer, Information filters, input images, input style image, learning (artificial intelligence), loss function, multitarget loss, neural nets, neural style transfer, output image, pre-trained deep convolutional neural network VGG19, Predictive Metrics, pubcrawl, Resiliency, Scalability, visualization |
| Abstract | Transferring the style of an image is a fundamental problem in computer vision. Which extracts the features of a context image and a style image, then fixes them to produce a new image with features of the both two input images. In this paper, we introduce an artificial system to separate and recombine the content and style of arbitrary images, providing a neural algorithm for the creation of artistic images. We use a pre-trained deep convolutional neural network VGG19 to extract the feature map of the input style image and context image. Then we define a loss function that captures the difference between the output image and the two input images. We use the gradient descent algorithm to update the output image to minimize the loss function. Experiment results show the feasibility of the method. |
| DOI | 10.1109/I-SPAN.2018.00057 |
| Citation Key | wang_image_2018 |
- fundamental problem
- visualization
- pre-trained deep convolutional neural network VGG19
- output image
- neural nets
- multitarget loss
- loss function
- learning (artificial intelligence)
- input style image
- input images
- Information filters
- image style transfer
- Image reconstruction
- gradient methods
- neural style transfer
- Filter banks
- feature map
- feature extraction
- context image
- content style
- computer vision
- artistic images
- arbitrary images
- pubcrawl
- Predictive Metrics
- Resiliency
- Scalability