• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Software Engineering and Service Science >A Transfer Learning Method Based on Residual Block
【24h】

A Transfer Learning Method Based on Residual Block

机译：一种基于残差块的转移学习方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In order to obtain high image representations in limited amount of datasets, a transfer learning method based on residual block is proposed. In this method, we follow a transfer learning approach by increasing the number of layers of the network to extract the higher order statistical features of the image. The main idea is to conduct feature transfer by means of ResNet (Deep Residual Network) model with setting ImageNet dataset as source domain. Firstly, all image data are preprocessed with data enhancement. Then, on the basis of modifying the source model's fully-connected classification layer, the adjustment module--residual block is added to the end of the network. Finally, after training the adjustment module, the deep model is achieved. Through transfer learning and deep feature extraction, the capability of feature recognition that impacted by content differences between source domain and target domain will be improved. Experiments show that our method achieves 97.98% accuracy on MNIST dataset and 90.45% accuracy on CIFAR-10 dataset, respectively. The experimental results demonstrate that the performance of our proposed method is significantly better than the existing transfer learning methods.
机译：为了获得有限量的数据集中的高图像表示，提出了一种基于残差块的传输学习方法。在该方法中，我们通过增加网络的层数来遵循传输学习方法，以提取图像的更高阶统计特征。主要思想是通过Reset（深度剩余网络）模型进行特征传输，其中将想象成数据集设置为源域。首先，所有图像数据都预处理数据增强。然后，在修改源模型的完全连接的分类层的基础上，调整模块 - 剩余块被添加到网络的末尾。最后，在训练调整模块之后，实现了深度模型。通过传输学习和深度特征提取，将提高由源域和目标域之间的内容差异影响的特征识别能力。实验表明，我们的方法分别在Mnist DataSet上实现了97.98％的准确性，分别在CiFar-10数据集中获得了90.45％的准确性。实验结果表明，我们提出的方法的性能明显优于现有的转移学习方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号