Search

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. [ABSTRACT FROM AUTHOR]

Aiming at the problem of confidentiality management of digital archives on the cloud, this paper presents an effective solution. The basic idea is to deploy a local server between the cloud and each client of an archive system to run a confidentiality management model of digital archives on the cloud, which includes an archive release model, and an archive search model. (1) The archive release model is used to strictly encrypt each archive file and archive data released by an administrator and generate feature data for the archive data, and then submit them to the cloud for storage to ensure the security of archive-sensitive data. (2) The archive search model is used to transform each query operation defined on the archive data submitted by a searcher, so that it can be correctly executed on feature data on the cloud, to ensure the accuracy and efficiency of archive search. Finally, both theoretical analysis and experimental evaluation demonstrate the good performance of the proposed solution. The result shows that compared with others, our solution has better overall performance in terms of confidentiality, accuracy, efficiency and availability, which can improve the security of archive-sensitive data on the untrusted cloud without compromising the performance of an existing archive management system. [ABSTRACT FROM AUTHOR]