arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.05809cs.LGcs.CVstat.ML
收藏

针对可量化表示的高效端到端学习

Efficient end-to-end learning for quantizable representations

Seoul National University(首尔大学)

Yeonwoo Jeong, Hyun Oh Song

摘要:

通过神经网络嵌入表示学习是现代基于相似性搜索的核心基础。虽然在开发用于学习二进制汉明码表示以提高搜索效率的算法方面已经投入了很多精力,但这仍然需要对每个查询的整个数据集进行线性扫描,并通过二进制化来权衡搜索精度。为此,我们考虑直接学习可量化的嵌入表示和稀疏二进制哈希码端到端的问题,其可用于构建有效的哈希表,不仅提供数据数量的显着搜索减少,而且还实现优于先前最先进的深度度量学习方法的最先进的搜索精度。我们还表明,找到最佳的稀疏二进制哈希码在一个小批量可以精确地计算在多项式时间通过解决最小成本流问题。我们在Cifar-100和ImageNet数据集上的结果显示,在precision@k和NMI指标方面,最先进的搜索精度,同时在穷举线性搜索上分别提供高达98倍和478倍的搜索加速。源代码可在https://github.com/maestrojeong/Deep-Hash-Table-ICML18上获得

英文摘要:

Embedding representation learning via neural networks is at the core foundation of modern similarity based search. While much effort has been put in developing algorithms for learning binary hamming code representations for search efficiency, this still requires a linear scan of the entire dataset per each query and trades off the search accuracy through binarization. To this end, we consider the problem of directly learning a quantizable embedding representation and the sparse binary hash code end-to-end which can be used to construct an efficient hash table not only providing significant search reduction in the number of data but also achieving the state of the art search accuracy outperforming previous state of the art deep metric learning methods. We also show that finding the optimal sparse binary hash code in a mini-batch can be computed exactly in polynomial time by solving a minimum cost flow problem. Our results on Cifar-100 and on ImageNet datasets show the state of the art search accuracy in precision@k and NMI metrics while providing up to 98X and 478X search speedup respectively over exhaustive linear search. The source code is available at https://github.com/maestrojeong/Deep-Hash-Table-ICML18

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。

↑