Research on image sentiment analysis technology based on sparse representation

CAAI Transactions on Intelligence Technology

article

Xiaofang Jin¹  Yinan Wu¹  Ying Xu¹  Chang Sun¹ 

[1] College of Information and Communication Engineering, Communication University of China;Academy of Broadcasting Science

关键词: FDL;    image sentiment analysis;    model efficiency;    sparse representation;    SVD;   

DOI  :  10.1049/cit2.12074

学科分类：数学（综合）

来源: Wiley

【 摘 要 】

Many methods based on deep learning have achieved amazing results in image sentiment analysis. However, these existing methods usually pursue high accuracy, ignoring the effect on model training efficiency. Considering that when faced with large-scale sentiment analysis tasks, the high accuracy rate often requires long experimental time. In view of the weakness, a method that can greatly improve experimental efficiency with only small fluctuations in model accuracy is proposed, and singular value decomposition (SVD) is used to find the sparse feature of the image, which are sparse vectors with strong discriminativeness and effectively reduce redundant information; The authors propose the Fast Dictionary Learning algorithm (FDL), which can combine neural network with sparse representation. This method is based on K-Singular Value Decomposition, and through iteration, it can effectively reduce the calculation time and greatly improve the training efficiency in the case of small fluctuation of accuracy. Moreover, the effectiveness of the proposed method is evaluated on the FER2013 dataset. By adding singular value decomposition, the accuracy of the test suite increased by 0.53%, and the total experiment time was shortened by 8.2%; Fast Dictionary Learning shortened the total experiment time by 36.3%.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND