...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Knowledge-Based Systems >Learning sparse features with lightweight ScatterNet for small sample training
【24h】

Learning sparse features with lightweight ScatterNet for small sample training

机译：学习稀疏功能，具有轻量级散射网，用于小型样本培训

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Convolutional neural networks (CNNs) have recently achieved impressive performances in image processing tasks such as image classification and object recognition. However, CNNs typically have a large number of parameters, leading to their requirement of a large number of training samples to extract spatial features. To address these limitations, we propose a lightweight ScatterNet with the learnable weight matrix and sparse transformation such as scale transformation and translation to learn sparse filters. This filter based on ScatterNet uses He initialization algorithm and learns from input images which are viewed as two-directional sequential data in the initial stage of model training. A Strip-Recurrent module sweeps both horizontally and vertically across the image to compress feature matrices. Then, ScatterNet decomposes the above feature matrices as a learned mixture of different harmonic functions to integrate the spectral analysis into CNNs. Finally, we combine the sequential and spectral features to build our hybrid architectures to complete image classification and segmentation. These architectures can obtain good classification accuracy on both small and large training datasets. Our proposed method is evaluated at both layer and network levels on five widely-used benchmark datasets: MNIST, CIFAR-10, CIFAR-100, Small NORB and Tiny ImageNet. We also study other small sample problems such as medical image segmentation and image classification based on few-shot learning. Experiments show that our proposed layer and hybrid model achieves better accuracy for small sample training. (C) 2020 Elsevier B.V. All rights reserved.
机译：卷积神经网络（CNNS）最近在图像处理任务中实现了令人印象深刻的性能，例如图像分类和对象识别。然而，CNN通常具有大量参数，导致它们要求大量训练样本来提取空间特征。为了解决这些限制，我们提出了一种轻量级的散射网，其中具有学习权重矩阵和稀疏变换，例如缩放转换和转换，以学习稀疏滤波器。基于散射网的该过滤器使用HE初始化算法，并从输入图像中学习，在模型训练的初始阶段中被视为双向顺序数据。条形复制模块在图像上水平和垂直扫描以压缩特征矩阵。然后，散射网将上述特征矩阵分解为不同谐波函数的学习混合物，以将光谱分析集成到CNN中。最后，我们结合了顺序和光谱功能来构建混合架构以完成图像分类和分割。这些架构可以在小型和大型训练数据集中获得良好的分类准确性。我们所提出的方法是在五个广泛使用的基准数据集中的层次和网络水平评估：Mnist，CiFar-10，CiFar-100，小型下降和微小想象。我们还基于几次拍摄学习研究了其他小型样本问题，如医学图像分割和图像分类。实验表明，我们所提出的层和混合模型实现了小型样本培训的更好准确性。 （c）2020 Elsevier B.v.保留所有权利。

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