原文传递
Transfer Learning in Convolutional Neural Networks for Fine-Grained Image Classification.
| 题名： | Transfer Learning in Convolutional Neural Networks for Fine-Grained Image Classification. |
| 作者： | Becherer, N. C. |
| 关键词： | Computer vision, Artificial neural networks, Algorithms, Artificial intelligence software, Computing system architectures, Signal processing, Pattern recognition, Computer languages, Machine learning, Supervised machine learning, Data set, Computer networks, Target recognition, Convolutional neural networks, Transfer learning, Parameter fine-tuning, Image classification |
| 摘要： | In recent years, convolutional neural networks have achieved state of the art performance in a number of computer vision problems such as image classification. Prior research has shown that a transfer learning technique known as parameter fine-tuning wherein a network is pre-trained on different datasets can boost the performance of these networks. However, the topic of identifying the best source dataset and learning strategy for a given target domain is largely unexplored. Thus, this research presents and evaluates various transfer learning methods for fine-grained image classification as well as the effect on ensemble networks. The main contributions are a framework to evaluate the effectiveness of transfer learning, an optimal strategy for parameter fine-tuning, and a thorough demonstration of its effectiveness. The experimental framework and findings will help to train models in reduced time and with improved accuracy for target recognition and automated aerial refueling. |
| 报告类型： | 科技报告 |
相关文献
- Convolutional Neural Networks For Detection And Classification Of Maritime Vessels In Electro-Optical Satellite Imagery.
- Estimating vehicle fuel economy from overhead camera imagery and application for traffic control
- Linear Layers and Partial Weight Reinitialization for Accelerating Neural Network Convergence.
- Automated Inventory and Analysis of Highway Assets. Phase II.
- Document Classification Techniques for Aviation Letters of Agreement.
- Fostering Positive Team Behaviors in Human Machine Teams Through Emotion Processing: Adapting to the Operator's State.
检索历史
应用推荐
