SemiMemes: A Semi-supervised Learning Approach for Multimodal Memes Analysis

被引:1
|
作者
Pham Thai Hoang Tung [1 ]
Nguyen Tan Viet [1 ]
Ngo Tien Anh [1 ]
Phan Duy Hung [1 ]
机构
[1] FPT Univ, Hanoi, Vietnam
关键词
Memes analysis; Multimodal learning; Semi-supervised learning;
D O I
10.1007/978-3-031-41456-5_43
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The prevalence of memes on social media has created the need to sentiment analyze their underlying meanings for censoring harmful content. Meme censoring systems by machine learning raise the need for a semi-supervised learning solution to take advantage of the large number of unlabeled memes available on the internet and make the annotation process less challenging. Moreover, the approach needs to utilize multimodal data as memes' meanings usually come from both images and texts. This research proposes a multimodal semi-supervised learning approach that outperforms other multimodal semi-supervised learning and supervised learning state-of-the-art models on two datasets, the Multimedia Automatic Misogyny Identification and Hateful Memes dataset. Building on the insights gained from Contrastive Language-Image Pre-training, which is an effective multimodal learning technique, this research introduces SemiMemes, a novel training method that combines auto-encoder and classification task to make use of the resourceful unlabeled data.
引用
收藏
页码:565 / 577
页数:13
相关论文
共 50 条
  • [1] Semi-supervised Learning with Multimodal Perturbation
    Su, Lei
    Liao, Hongzhi
    Yu, Zhengtao
    Tang, Jiahua
    ADVANCES IN NEURAL NETWORKS - ISNN 2009, PT 1, PROCEEDINGS, 2009, 5551 : 651 - +
  • [2] Multimodal semi-supervised learning for image classification
    Guillaumin, Matthieu
    Verbeek, Jakob
    Schmid, Cordelia
    2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, : 902 - 909
  • [3] SSLMM: Semi-Supervised Learning with Missing Modalities for Multimodal Sentiment Analysis
    Wang, Yiyu
    Jian, Haifang
    Zhuang, Jian
    Guo, Huimin
    Leng, Yan
    INFORMATION FUSION, 2025, 120
  • [4] A topological approach for semi-supervised learning
    Ines, A.
    Dominguez, C.
    Heras, J.
    Mata, G.
    Rubio, J.
    JOURNAL OF COMPUTATIONAL SCIENCE, 2024, 82
  • [5] ENHANCED SEMI-SUPERVISED LEARNING FOR MULTIMODAL EMOTION RECOGNITION
    Zhang, Zixing
    Ringeval, Fabien
    Dong, Bin
    Coutinho, Eduardo
    Marchi, Erik
    Schuller, Bjoern
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5185 - 5189
  • [6] A Theoretical Analysis of Semi-supervised Learning
    Fujii, Takashi
    Ito, Hidetaka
    Miyoshi, Seiji
    NEURAL INFORMATION PROCESSING, ICONIP 2016, PT II, 2016, 9948 : 28 - 36
  • [7] Analysis of active semi-supervised learning
    Berton, Lilian
    Mitsuishi, Felipe Baz
    Vega-Oliveros, Didier A.
    38TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2023, 2023, : 1122 - 1129
  • [8] Semi-Supervised Multimodal Representation Learning Through a Global Workspace
    Devillers, Benjamin
    Maytie, Leopold
    VanRullen, Rufin
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,
  • [9] Hypergraph Variational Autoencoder for Multimodal Semi-supervised Representation Learning
    Liu, Jingquan
    Du, Xiaoyong
    Li, Yuanzhe
    Hu, Weidong
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT IV, 2022, 13532 : 395 - 406
  • [10] An artificial life approach for semi-supervised learning
    Herrmann, Lutz
    Ultsch, Alfred
    DATA ANALYSIS, MACHINE LEARNING AND APPLICATIONS, 2008, : 139 - 146