CASIA OpenIR  > 脑图谱与类脑智能实验室  > 神经计算与脑机交互
Deep Modality Assistance Co-Training Network for Semi-Supervised Multi-Label Semantic Decoding
Dan Li; Changde Du; Haibao Wang; Qiongyi Zhou; Huiguang He
Source PublicationIEEE Transactions on Multimedia
2022-07
Volume24Pages:3287-3299
Abstract

Multi-label semantic decoding is a challenging task with great scientific significance and application value. The existing methods mainly focus on label learning and ignore the amount of information contained in the sample itself,especially non-image sample,which may limit their performance. To address these issues,we propose a novel semi-supervised modality assistance co-training network,which utilizes image modality to assist non-image modality for multi-label learning. In real application,there are two thorny issues: (i) non-image modality tends to be missing owing to the difficulty in obtaining them; (ii) although the image modality is easy to obtain from the Internet,image label annotation is still time-consuming and expensive. Therefore,the proposed method utilizes a small number of paired & labeled images and non-image modalities,and a large number of unpaired & unlabeled images from web sources to improve results. It consists of the modality-specific feature generators,the feature translators and the label relationship network. Specifically,the modality-specific feature generators are used to generate different features (views) for each modality. Semantic translators are employed to capture the relationship between the paired modalities and impute the missing modality feature by using unpaired & unlabeled images. Label relation network is a graph convolution network (GCN) aiming to capture the correlation between labels. To mine the information in unlabeled features,the co-training mechanism is considered. With this mechanism,we introduce a multi-view orthogonality constraint and a multi-label co-regularization constraint. Extensive experiments on three computer vision and neuroscience datasets demonstrate the effectiveness of the proposed method.

DOI10.1109/TMM.2021.3104980
Indexed BySCI
Sub direction classification脑机接口
planning direction of the national heavy laboratory人工智能基础前沿理论
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/50896
Collection脑图谱与类脑智能实验室_神经计算与脑机交互
Corresponding AuthorHuiguang He
Recommended Citation
GB/T 7714
Dan Li,Changde Du,Haibao Wang,et al. Deep Modality Assistance Co-Training Network for Semi-Supervised Multi-Label Semantic Decoding[J]. IEEE Transactions on Multimedia,2022,24:3287-3299.
APA Dan Li,Changde Du,Haibao Wang,Qiongyi Zhou,&Huiguang He.(2022).Deep Modality Assistance Co-Training Network for Semi-Supervised Multi-Label Semantic Decoding.IEEE Transactions on Multimedia,24,3287-3299.
MLA Dan Li,et al."Deep Modality Assistance Co-Training Network for Semi-Supervised Multi-Label Semantic Decoding".IEEE Transactions on Multimedia 24(2022):3287-3299.
Files in This Item: Download All
File Name/Size DocType Version Access License
J70-Deep Modality As(2627KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Dan Li]'s Articles
[Changde Du]'s Articles
[Haibao Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Dan Li]'s Articles
[Changde Du]'s Articles
[Haibao Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Dan Li]'s Articles
[Changde Du]'s Articles
[Haibao Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: J70-Deep Modality Assistance Co-Training Network for Semi-Supervised Multi-Label Semantic Decoding.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.