Deakin University
Browse

File(s) under embargo

Unbalanced Multi-view Deep Learning

conference contribution
posted on 2024-01-05, 04:12 authored by C Xu, Z Li, Z Guan, W Zhao, X Song, Y Wu, Jianxin LiJianxin Li
Most existing multi-view learning methods assume that the dimensions of different views are similar. In real-world applications, it is often the case that the dimension of a view may be extremely small compared with these of other views, resulting in an unbalanced multi-view learning problem. Previous methods for this problem have at least one of the following drawbacks: (1) despising the information of low dimensional views; (2) constructing balanced view-specific inter-instance similarity graphs or employing decision-level fusion, which cannot well learn multi-level inter-view correlations and is limited to category-related tasks such as clustering. To eliminate all these drawbacks, we present an Unbalanced Multi-view Deep Learning (UMDL) method. Considering a low dimensional view usually contains multiple patterns, we construct an overcomplete dictionary with its atoms exceeding the dimension of the original data. We transfer the original data into a combination of atoms and obtain a higher dimensional representation. We propose a sparse multi-view fusion paradigm to explicitly capture the complementarity of multi-view data in a flexible manner. Moreover, we construct positive and negative examples via balanced similarity graphs and employ contrastive learning to train UMDL in a self-supervised manner. Experiments conducted on a toy example and 7 balanced/unbalanced datasets show that UMDL outperforms baseline methods and can be well applied to downstream classification and segmentation tasks. The code is released at https://github.com/xdmvteam/UMDL.

History

Pagination

3051-3059

Location

Ottawa, Canada

Start date

2023-10-29

End date

2023-11-02

ISBN-13

9798400701085

Language

eng

Publication classification

E1 Full written paper - refereed

Title of proceedings

MM 2023 : Proceedings of the 31st ACM International Conference on Multimedia 2023

Event

ACM Multimedia. Conference (2023 : Ottawa, Canada)

Publisher

ACM Digital Library

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC