Sparse autoencoder for social image understanding

Jianran Liu

doi:10.1016/j.neucom.2019.08.083

Return

Sparse autoencoder for social image understanding

2019-12-01

PRE

DOI：10.1016/j.neucom.2019.08.083

Original

Original request for help

Save

Abstract

En 中文

The rapid increase of social media images has made organizing these resources effectively a huge problem. Labeling unlabeled images becomes the crucial division of social image understanding. However, the enhancement of social image sharpness leads to the increase of surface feature dimension. These multidimensional complex features leads to the curse of dimensionality and the difficulty of feature extraction. In this paper, sparse autoencoder is studied to solve the problem of social image understanding, because sparse autoencoder can make these features represent the original data in a refined way, thus avoiding curse of dimensionality as much as possible and significantly improve the understanding effect. First, we explore the dimensional reduction capability of sparse autoencoder, and use sparse autoencoder to get low-dimensional features. Second, for low-dimensional features, an enhanced multi-label classifier is utilized to assign labels with the help of cosine similarity about tags correlation. The ability of dimensionality reduction of sparse autoencoder is proved by mapping matrix of image-label. Finally, we test our approach on several publicly available social media datasets. The results demonstrate that our proposed method is superior to lots of non-deep learning method among three evaluation indexes of social image understanding. (C) 2019 Elsevier B.V. All rights reserved.

Keywords:

Machine learning

Dimensionality reduction

Image understanding

Sparse autoencoder

Multi-label predict

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.