Visualization Methods for Image Transformation Convolutional Neural Networks
Autor: | Jose Douglas Bratti, Paulo Drews, Eglen Protas, Silvia Silva da Costa Botelho, Joel Felipe de Oliveira Gaya |
---|---|
Rok vydání: | 2019 |
Předmět: |
Computer Networks and Communications
Computer science media_common.quotation_subject Image processing 02 engineering and technology Machine learning computer.software_genre Convolutional neural network Pattern Recognition Automated Artificial Intelligence Image Processing Computer-Assisted 0202 electrical engineering electronic engineering information engineering Humans Sensory cue Image restoration media_common Creative visualization Artificial neural network business.industry Computer Science Applications Visualization Pattern recognition (psychology) 020201 artificial intelligence & image processing Neural Networks Computer Artificial intelligence business computer Software |
Zdroj: | IEEE Transactions on Neural Networks and Learning Systems. 30:2231-2243 |
ISSN: | 2162-2388 2162-237X |
Popis: | Convolutional neural networks (CNNs) are powerful machine learning models that have become the state of the art in several problems in the areas of computer vision and image processing. Nevertheless, the knowledge of why and how these models present an impressive performance is still limited. There are visualization techniques that can help us to understand the inner working of neural networks. However, they have mostly been applied to classification models. In this paper, we evaluate the application of visualization methods to networks where the input and output are images of proportional dimensions. The results show that visualization brings visual cues associated with how these systems work, helping in their understanding and improvement. We use the knowledge obtained from the visualization of an image restoration CNN to improve the architecture's efficiency with no significant degradation of its performance. |
Databáze: | OpenAIRE |
Externí odkaz: |