Feature-level fusion of convolutional neural networks for visual object classification
| Autor: | Hilal Ergun, Mustafa Sert |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Contextual image classification
Artificial neural network Computer science business.industry Deep learning Pooling 02 engineering and technology Pascal (programming language) 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Convolutional neural network Residual neural network Bag-of-words model in computer vision Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer 0105 earth and related environmental sciences computer.programming_language |
| Zdroj: | SIU |
| DOI: | 10.1109/siu.2016.7496204 |
| Popis: | Deep learning architectures have shown great success in various computer vision applications. In this study, we investigate some of the very popular convolutional neural network (CNN) architectures, namely GoogleNet, AlexNet, VGG19 and ResNet. Furthermore, we show possible early feature fusion strategies for visual object classification tasks. Concatanation of features, average pooling and maximum pooling are among the investigated fusion strategies. We obtain state-of-the-art results on well-known image classification datasets of Caltech-101, Caltech-256 and Pascal VOC 2007. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|