EGD: Error-Entropy-Guided Distillation for Noisy Multi-View Classification
Open Access
- 10 April 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (8) , 1596
Abstract
In recent years, multi-view learning has received extensive research interest. Most existing multi-view learning methods often rely on well-annotated data to improve decision accuracy. However, noisy labels are ubiquitous in multi-view data due to imperfect annotations. Although some methods have achieved promising performance using robust-loss designs and implicit regularization, they fail to explicitly model the reliability of the supervision signal and fail to dynamically correct noisy labels during training. Clearly, this largely constrains their performance ceiling. To deal with this problem, we propose an Error-Entropy-Guided Distillation network (EGD) for noisy multi-view classification. In this framework, we first design an Error-Entropy (EE) metric to explicitly evaluate the reliability of sample-wise supervision, which serves as the basis for identifying and filtering noisy labels. On this basis, we adopt the distillation paradigm based on Error-Entropy (EE). The teacher model provides the student with soft label distributions that are less affected by noisy labels in the early training stage. To further mitigate noise memorization and accumulated confirmation bias, we propose a periodic memory-clearing strategy and supervision signal update strategy to prevent the teacher from error memorization and accumulating confirmation bias. Meanwhile, the student model learns from the soft supervision of the teacher to capture structured inter-class relationships. Additionally, a consistency module is employed to enhance the consistency of the student across multiple views. Extensive experiments on five benchmark datasets demonstrate that EGD consistently outperforms state-of-the-art multi-view learning methods under various noise levels.Keywords
Funding Information
- APC
This publication has 20 references indexed in Scilit:
- Domain adaptation using transformer models for automated detection of exterior cladding materials in street view imagesScientific Reports, 2025
- Reliable Representation Learning for Incomplete Multi-View Missing Multi-Label ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
- Robust Multi-View Clustering With Noisy CorrespondenceIEEE Transactions on Knowledge and Data Engineering, 2024
- Cross-view Graph Matching Guided Anchor Alignment for Incomplete Multi-view ClusteringInformation Fusion, 2023
- Label-noise robust classification with multi-view learningScience China Technological Sciences, 2023
- Deep Double Incomplete Multi-View Multi-Label Learning With Incomplete Labels and Missing ViewsIEEE Transactions on Neural Networks and Learning Systems, 2023
- Hierarchical Hashing Learning for Image Set ClassificationIEEE Transactions on Image Processing, 2023
- Dual Contrastive Prediction for Incomplete Multi-View Representation LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Trusted Multi-View Classification With Dynamic Evidential FusionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Latent Semantic Aware Multi-View Multi-Label ClassificationProceedings of the AAAI Conference on Artificial Intelligence, 2018