Learning a Fine Vocabulary
Learning a Fine Vocabulary
复制标题
DOI：
10.1007/978-3-642-15558-1_1
复制
发表时间：
2010-09
期刊：
影响因子：
--
通讯作者：
Andrej Mikulík;Michal Perdoch;Ondřej Chum;Jiri Matas
中科院分区：
文献类型：
--
作者：
Andrej Mikulík;Michal Perdoch;Ondřej Chum;Jiri Matas
提出了一种新的词袋式大规模图像检索的相似度度量方法。相似函数以无监督的方式学习，比标准词袋方法不需要额外的空间，并且比基于l2的软分配和Hamming嵌入更具判别性。我们通过实验证明，新的相似函数达到了平均精度，优于在许多标准数据集上发表的文献中的任何结果。同时，使用该相似度函数的检索速度比参考方法快。
A novel similarity measure for bag-of-words type large scale image retrieval is presented. The similarity function is learned in an unsupervised manner, requires no extra space over the standard bag-of-words method and is more discriminative than both L2-based soft assignment and Hamming embedding.We show experimentally that the novel similarity function achieves mean average precision that is superior to any result published in the literature on a number of standard datasets. At the same time, retrieval with the proposed similarity function is faster than the reference method.