File(s) under permanent embargo
Unsupervised deep features for privacy image classification
conference contribution
posted on 2019-01-01, 00:00 authored by Chiranjibi Sitaula, Yong XiangYong Xiang, Sunil AryalSunil Aryal, Xuequan LuSharing images online poses security threats to a wide range of users due to the unawareness of privacy information. Deep features have been demonstrated to be a powerful representation for images. However, deep features usually suffer from the issues of a large size and requiring a huge amount of data for fine-tuning. In contrast to normal images (e.g., scene images), privacy images are often limited because of sensitive information. In this paper, we propose a novel approach that can work on limited data and generate deep features of smaller size. For training images, we first extract the initial deep features from the pre-trained model and then employ the K-means clustering algorithm to learn the centroids of these initial deep features. We use the learned centroids from training features to extract the final features for each testing image and encode our final features with the triangle encoding. To improve the discriminability of the features, we further perform the fusion of two proposed unsupervised deep features obtained from different layers. Experimental results show that the proposed features outperform state-of-the-art deep features, in terms of both classification accuracy and testing time.
History
Event
Image and Video Technology. Pacific-Rim Symposium (9th : 2019 : Sydney, N.S.W.)Volume
11854Series
Lecture Notes in Computer SciencePagination
404 - 415Publisher
SpringerLocation
Sydney, N.S.W.Place of publication
Cham, SwitzerlandPublisher DOI
Start date
2019-11-18End date
2019-11-22ISSN
0302-9743eISSN
1611-3349ISBN-13
9783030348786ISBN-10
3030348792Language
engPublication classification
E1 Full written paper - refereedEditor/Contributor(s)
C Lee, Z Su, A SugimotoTitle of proceedings
Image and video technology : 9th Pacific-Rim Symposium, PSIVT 2019, Sydney, NSW, Australia, November 18-22, 2019, ProceedingsUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC