Deep Convolutional Neural Networks as Generic Feature Extractors
| Autor: | Lars Hertel, Thomas Martinetz, Erhardt Barth, Thomas Käster |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
Computer science business.industry Deep learning Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Computer Science - Neural and Evolutionary Computing Pattern recognition Machine learning computer.software_genre Convolutional neural network Task (project management) Machine Learning (cs.LG) Computer Science - Learning Kernel (image processing) Handwriting recognition Feature (machine learning) Artificial intelligence Neural and Evolutionary Computing (cs.NE) business computer |
| Zdroj: | IJCNN |
| DOI: | 10.48550/arxiv.1710.02286 |
| Popis: | Recognizing objects in natural images is an intricate problem involving multiple conflicting objectives. Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task. However, the long time needed to train such deep networks is a major drawback. We tackled this problem by reusing a previously trained network. For this purpose, we first trained a deep convolutional network on the ILSVRC2012 dataset. We then maintained the learned convolution kernels and only retrained the classification part on different datasets. Using this approach, we achieved an accuracy of 67.68 % on CIFAR-100, compared to the previous state-of-the-art result of 65.43 %. Furthermore, our findings indicate that convolutional networks are able to learn generic feature extractors that can be used for different tasks. Comment: 4 pages, accepted version for publication in Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), July 2015, Killarney, Ireland |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|