arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.09563cs.LGcs.CVeess.IV
收藏

在线卷积字典学习

Online Convolutional Dictionary Learning

UCLA(加州大学洛杉矶分校);Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室)

Jialin Liu, Cristina Garcia-Cardona, Brendt Wohlberg, Wotao Yin

摘要:

虽然最近已经提出了许多不同的算法用于卷积字典学习,但这仍然是一个昂贵的问题。从大型训练集学习的最大障碍是内存需求,由于所有现有方法都是批处理算法,内存需求至少与训练集的大小呈线性增长。本文报告的工作通过将在线词典学习思想扩展到卷积上下文来解决这一限制。

英文摘要:

While a number of different algorithms have recently been proposed for convolutional dictionary learning, this remains an expensive problem. The single biggest impediment to learning from large training sets is the memory requirements, which grow at least linearly with the size of the training set since all existing methods are batch algorithms. The work reported here addresses this limitation by extending online dictionary learning ideas to the convolutional context.

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。

↑