当前位置: X-MOL 学术IEEE Access › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Pseudo Labels and Soft Multi-Part Corresponding Similarity for Unsupervised Deep Hashing
IEEE Access ( IF 3.4 ) Pub Date : 2020-03-17 , DOI: 10.1109/access.2020.2981288
Huiying Li 1 , Yang Li 1 , Xin Xie 1 , Shuai Gao 1 , Dongsheng Mao 1
Affiliation  

In recent years, unsupervised deep hashing methods have achieved great success in large-scale image retrieval. However, these approaches still suffer two major problems in real world applications. On the one hand, due to the lack of effective supervision information, hash codes of different categories are easily judged to be similar. On the other hand, binary semantic similarity matrices can not reflect ranking relationship and the internal structure information of different images. To solve these problems, we propose a novel unsupervised deep hashing method, named Pseudo labels and Soft multi-part Corresponding similarity based Hashing (PSCH), to ensure the heterogeneity of the hash codes. Specifically, we propose a “pseudo labels” method that use k{k} -means clustering and a distance threshold to generate the pseudo labels. Further, in order to reflect the hash codes similarity between instances within the same class, we propose a novel soft multi-part corresponding similarity method to learn better hash codes. This method can divide deep feature maps into several groups and compute the attention map for multi-part similarity matrices. In addition, a novel loss function is proposed to support learning with pseudo labels and soft multi-part corresponding similarity for achieving better performance. Comprehensive experiments on CIFAR-10, NUSWIDE, and Flickr demonstrate that our method can generate high-quality hash codes and outperform state-of-the-art unsupervised hashing methods by a large margin.

中文翻译:


无监督深度哈希的伪标签和软多部分对应相似度



近年来,无监督深度哈希方法在大规模图像检索中取得了巨大成功。然而,这些方法在现实世界的应用中仍然面临两个主要问题。一方面,由于缺乏有效的监管信息,不同类别的哈希码很容易被判断为相似。另一方面,二值语义相似度矩阵不能反映不同图像的排序关系和内部结构信息。为了解决这些问题,我们提出了一种新颖的无监督深度哈希方法,称为伪标签和基于软多部分对应相似性哈希(PSCH),以确保哈希码的异构性。具体来说,我们提出了一种“伪标签”方法,该方法使用 k{k} 均值聚类和距离阈值来生成伪标签。此外,为了反映同一类内实例之间的哈希码相似性,我们提出了一种新颖的软多部分对应相似性方法来学习更好的哈希码。该方法可以将深度特征图分为几组,并计算多部分相似度矩阵的注意力图。此外,还提出了一种新颖的损失函数来支持伪标签和软多部分对应相似性的学习,以实现更好的性能。在 CIFAR-10、NUSWIDE 和 Flickr 上的综合实验表明,我们的方法可以生成高质量的哈希代码,并且大大优于最先进的无监督哈希方法。
更新日期:2020-03-17
down
wechat
bug