Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Trusted Semi-Supervised Multi-View Classification With Contrastive Learning
AU - Wang, Xiaoli
AU - Wang, Yongli
AU - Wang, Yupeng
AU - Huang, Anqi
AU - Liu, Jun
PY - 2024/12/31
Y1 - 2024/12/31
N2 - Semi-supervised multi-view learning is a remarkable but challenging task. Existing semi-supervised multi-view classification (SMVC) approaches mainly focus on performance improvement while ignoring decision reliability, which limits their deployment in safety-critical applications. Although several trusted multi-view classification methods are proposed recently, they rely on manual annotations. Therefore, this work emphasizes trusted multi-view classification learning under semi-supervised conditions. Different from existing SMVC methods, this work jointly models class probabilities and uncertainties based on evidential deep learning to formulate view-specific opinions. Moreover, unlike previous works that explore cross-view consistency in a single schema, this work proposes a multi-level consistency constraint. Specifically, we explore instance-level consistency on the view-specific representation space and category-level consistency on opinions from multiple views. Our proposed trusted graph-based contrastive loss nicely establishes the relationship between joint opinions and view-specific representations, which enables view-specific representations to enjoy a good manifold to improve classification performance. Overall, the proposed approach provides reliable and superior semi-supervised multi-view classification decisions. Extensive experiments demonstrate the effectiveness, reliability and robustness of the proposed model.
AB - Semi-supervised multi-view learning is a remarkable but challenging task. Existing semi-supervised multi-view classification (SMVC) approaches mainly focus on performance improvement while ignoring decision reliability, which limits their deployment in safety-critical applications. Although several trusted multi-view classification methods are proposed recently, they rely on manual annotations. Therefore, this work emphasizes trusted multi-view classification learning under semi-supervised conditions. Different from existing SMVC methods, this work jointly models class probabilities and uncertainties based on evidential deep learning to formulate view-specific opinions. Moreover, unlike previous works that explore cross-view consistency in a single schema, this work proposes a multi-level consistency constraint. Specifically, we explore instance-level consistency on the view-specific representation space and category-level consistency on opinions from multiple views. Our proposed trusted graph-based contrastive loss nicely establishes the relationship between joint opinions and view-specific representations, which enables view-specific representations to enjoy a good manifold to improve classification performance. Overall, the proposed approach provides reliable and superior semi-supervised multi-view classification decisions. Extensive experiments demonstrate the effectiveness, reliability and robustness of the proposed model.
U2 - 10.1109/TMM.2024.3379079
DO - 10.1109/TMM.2024.3379079
M3 - Journal article
VL - 26
SP - 8268
EP - 8278
JO - IEEE Transactions on Multimedia
JF - IEEE Transactions on Multimedia
SN - 1520-9210
ER -