.png){kind=icon}
返回
Progressive Deep Non-Negative Matrix Factorization Architecture with Graph Convolution-based Basis Image Reorganization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108984.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep non-negative matrix factorization is committed to using multi-layer structure to extract underlying parts-based representation. However, the basis images obtained by continuous depth factorization is too sparse, resulting in too fragmented parts reflected by the basis image. This makes the number of factor-ization layers limited and the underlying local feature representation is inaccurate. Therefore, we propose a novel progressive deep non-negative matrix factorization (PDNMF) architecture that adds a basis image reconstruction step to the successive basis image factorization steps. This helps the basis image in depth factorization to maintain better robustness of feature representation. In the reconstruction step, the at-tribute similarity graph (ASG) is constructed to describe the semantic expression ability of each basis image. With the help of the ASG, the basis image enhances its own semantic integrity through graph convolution without drastically destroying its representation. The evaluation in image recognition shows that the recognition accuracy of the proposed PDNMF improves with the increase of layers. Our method outperforms the state-of-the-art deep factorization methods in image recognition.(c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Deep non -negative matrix factorization
Graph convolution
Basis image reconstruction
Basis image factorization
Face recognition
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
The FERET database and evaluation procedure for face-recognition algorithms人脸识别算法的FERET数据库和评估程序
.png){kind=icon}
PREAI
分享收藏
分享收藏
Long-Term Health Monitoring of in-Service Bridge Deck by Covariance of Covariance Matrix of Acceleration Responses基于加速度响应协方差矩阵的在役桥面长期健康监测
PREAI
分享收藏分享收藏
查看更多内容