首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition >Learning Structure and Strength of CNN Filters for Small Sample Size Training
【24h】

Learning Structure and Strength of CNN Filters for Small Sample Size Training

机译:小样本量训练的CNN滤波器的学习结构和强度

获取原文

摘要

Convolutional Neural Networks have provided state-of-the-art results in several computer vision problems. However, due to a large number of parameters in CNNs, they require a large number of training samples which is a limiting factor for small sample size problems. To address this limitation, we propose SSF-CNN which focuses on learning the 'structure' and 'strength' of filters. The structure of the filter is initialized using a dictionary based filter learning algorithm and the strength of the filter is learned using the small sample training data. The architecture provides the flexibility of training with both small and large training databases, and yields good accuracies even with small size training data. The effectiveness of the algorithm is first demonstrated on MNIST, CIFAR10, and NORB databases, with varying number of training samples. The results show that SSF-CNN significantly reduces the number of parameters required for training while providing high accuracies on the test databases. On small sample size problems such as newborn face recognition and Omniglot, it yields state-of-the-art results. Specifically, on the IIITD Newborn Face Database, the results demonstrate improvement in rank-1 identification accuracy by at least 10%.
机译:卷积神经网络提供了一些计算机视觉问题的最新结果。但是,由于CNN中有大量参数,因此它们需要大量训练样本,这是小样本规模问题的限制因素。为了解决这个限制,我们提出了SSF-CNN,其重点是学习过滤器的“结构”和“强度”。使用基于字典的过滤器学习算法初始化过滤器的结构,并使用小的样本训练数据来学习过滤器的强度。该体系结构提供了使用小型和大型培训数据库进行培训的灵活性,即使使用小型培训数据也能产生良好的准确性。该算法的有效性首先在MNIST,CIFAR10和NORB数据库上得到了证明,并带有不同数量的训练样本。结果表明,SSF-CNN大大减少了训练所需的参数数量,同时在测试数据库上提供了较高的准确性。对于诸如新生儿脸部识别和Omniglot之类的小样本量问题,它可以提供最新的结果。具体而言,在IIITD新生儿面部数据库上,结果表明,rank-1识别准确性至少提高了10%。

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