文献类型：期刊文献

英文题名：PLDH: Pseudo-Labels Based Deep Hashing

作者：Liu, Huawen[1];Yin, Minhao[2];Wu, Zongda[1];Zhao, Liping[1];Li, Qi[1];Zhu, Xinzhong[3];Zheng, Zhonglong[3]

机构：[1]Shaoxing Univ, Dept Comp Sci, Shaoxing 312000, Peoples R China;[2]Northeast Normal Univ, Sch Informat Sci & Technol, Changchun 130024, Peoples R China;[3]Zhejiang Normal Univ, Sch Comp Sci & Technol, Jinhua 311231, Peoples R China

年份：2023

卷号：11

期号：9

外文期刊名：MATHEMATICS

收录：SCI-EXPANDED(收录号：WOS:000986748800001)、、Scopus(收录号：2-s2.0-85159151711)、WOS

基金：This work was partially funded by the Natural Science Foundation (NSF) of China (No. 61976195, 62271321, 62272419, 61976196, 62002226) and the Natural Science Foundation of Zhejiang Province (No. LZ23F020003, LR23F020001, LZ22F020010), Outstanding Talents of "Ten Thousand Talents Plan" in Zhejiang Province (No. 2018R51001), and the Science and Technology Plan Project in Basic Public Welfare class of Shaoxing city (No.2022A11002).

语种：英文

外文关键词：learning to hash; image retrieval; deep learning; nearest neighbor search; unsupervised learning; pseudo-label

外文摘要：Deep hashing has received a great deal of attraction in large-scale data analysis, due to its high efficiency and effectiveness. The performance of deep hashing models heavily relies on label information, which is very expensive to obtain. In this work, a novel end-to-end deep hashing model based on pseudo-labels for large-scale data without labels is proposed. The proposed hashing model consists of two major stages, where the first stage aims to obtain pseudo-labels based on deep features extracted by a pre-training deep convolution neural network. The second stage generates hash codes with high quality by the same neural network in the previous stage, coupled with an end-to-end hash layer, whose purpose is to encode data into a binary representation. Additionally, a quantization loss is introduced and interwound within these two stages. Evaluation experiments were conducted on two frequently-used image collections, CIFAR-10 and NUS-WIDE, with eight popular shallow and deep hashing models. The experimental results show the superiority of the proposed method in image retrieval.