Back to Search
Start Over
Visualizing deep neural network by alternately image blurring and deblurring
- Source :
- Neural Networks. 97:162-172
- Publication Year :
- 2018
- Publisher :
- Elsevier BV, 2018.
-
Abstract
- Visualization from trained deep neural networks has drawn massive public attention in recent. One of the visualization approaches is to train images maximizing the activation of specific neurons. However, directly maximizing the activation would lead to unrecognizable images, which cannot provide any meaningful information. In this paper, we introduce a simple but effective technique to constrain the optimization route of the visualization. By adding two totally inverse transformations, image blurring and deblurring, to the optimization procedure, recognizable images can be created. Our algorithm is good at extracting the details in the images, which are usually filtered by previous methods in the visualizations. Extensive experiments on AlexNet, VGGNet and GoogLeNet illustrate that we can better understand the neural networks utilizing the knowledge obtained by the visualization.
- Subjects :
- Neurons
Deblurring
Artificial neural network
Computer science
business.industry
Cognitive Neuroscience
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
Image (mathematics)
Visualization
Machine Learning
Artificial Intelligence
020204 information systems
Image Processing, Computer-Assisted
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Computer vision
Neural Networks, Computer
Artificial intelligence
business
Algorithms
Subjects
Details
- ISSN :
- 08936080
- Volume :
- 97
- Database :
- OpenAIRE
- Journal :
- Neural Networks
- Accession number :
- edsair.doi.dedup.....0b0e06a6edc13f0a02a93ac0aac35bf3