Abstract
Traditional person re-identification (ReID) methods typically represent person images as real-valued features, which makes ReID inefficient when the gallery set is extremely large. Recently, some hashing methods have been proposed to make ReID more efficient. However, these hashing methods will deteriorate the accuracy in general, and the efficiency of them is still not high enough. In this paper, we propose a novel hashing method, called deep multi-index hashing (DMIH), to improve both efficiency and accuracy for ReID. DMIH seamlessly integrates multi-index hashing and multi-branch based networks into the same framework. Furthermore, a novel block-wise multi-index hashing table construction approach and a search-aware multi-index (SAMI) loss are proposed in DMIH to improve the search efficiency. Experiments on three widely used datasets show that DMIH can outperform other state-of-the-art baselines, including both hashing methods and real-valued methods, in terms of both efficiency and accuracy.
Abstract (translated)
传统的人再识别(REID)方法通常将人的图像表示为真正有价值的特征,这使得当画廊集非常大时REID效率低下。最近,人们提出了一些散列方法来提高REID的效率。然而,这些散列方法通常会降低精度,而且效率仍然不够高。为了提高REID的效率和准确性,本文提出了一种新的哈希方法,即深度多索引哈希法。DMIH无缝地将多索引散列和基于多分支的网络集成到同一个框架中。此外,为了提高搜索效率,提出了一种新的分块多索引哈希表构造方法和一种搜索感知多索引(SAMI)损失。对三个广泛使用的数据集进行的实验表明,DMIH在效率和准确性方面优于其他最先进的基线,包括散列方法和实值方法。
URL
https://arxiv.org/abs/1905.10980