arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10495cs.CVcs.LG
收藏

卷积网络中用于一次性学习的排序池化

Sorted Pooling in Convolutional Networks for One-shot Learning

Peter Pazmany Catholic University(帕兹马尼·彼得天主教大学)

András Horváth

摘要:

我们提出了通用版本的常用的最大池化操作:$k$ th最大和排序池化操作,选择$k$ th最大的响应在每个池化区域,选择本地一致的输入图像的功能。该方法能够提高网络的泛化能力,并可用于减少网络的训练时间和出错率,并且在可用数据量有限的训练场景(如一次性学习场景)的情况下,该方法可以显著提高准确性

英文摘要:

We present generalized versions of the commonly used maximum pooling operation: $k$th maximum and sorted pooling operations which selects the $k$th largest response in each pooling region, selecting locally consistent features of the input images. This method is able to increase the generalization power of a network and can be used to decrease training time and error rate of networks and it can significantly improve accuracy in case of training scenarios where the amount of available data is limited, like one-shot learning scenarios

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑