Using very deep autoencoders for content-based image retrieval

Using very deep autoencoders for content-based image retrieval
复制标题

DOI:
--
复制
发表时间:
2011
期刊:
--
影响因子:
--
通讯作者:
A. Krizhevsky;Geoffrey E. Hinton
A. Krizhevsky;Geoffrey E. Hinton
中科院分区:
其他
文献类型:
--
作者:
A. Krizhevsky;Geoffrey E. Hinton

文献摘要

被引文献

相似文献

我们展示了如何在彩色图像上学习许多层特征,并使用这些特征初始化深度自编码器。然后我们使用自动编码器将图像映射为短二进制代码。使用语义哈希[6],28位代码可用于检索与查询图像相似的图像,时间与数据库的大小无关。这种极快的检索使得使用查询图像的多个不同转换进行搜索成为可能。256位二进制代码允许更精确的匹配,并且可以用来修剪使用28位代码找到的图像集。
We show how to learn many layers of features on color images and we use these features to initialize deep autoencoders. We then use the autoencoders to map images to short binary codes. Using semantic hashing [6], 28-bit codes can be used to retrieve images that are similar to a query image in a time that is independent of the size of the database. This extremely fast retrieval makes it possible to search using multiple di erent transformations of the query image. 256-bit binary codes allow much more accurate matching and can be used to prune the set of images found using the 28-bit codes.