mlsanityData to 14 Oct 2026

Trusted Multi-View Classification with Dynamic Evidential Fusion

arXiv 2204.11423 ↗First posted 25 Apr 2022cs.LGcited by 168

Not on the map. Why?

Abstract (arXiv)

Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks. Although effective, it is also crucial to ensure the reliability of both the multi-view integration and the final decision, especially for noisy, corrupted and out-of-distribution data. Dynamically assessing the trustworthiness of each view for different samples could provide reliable integration. This can be achieved through uncertainty estimation. With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed TMC can promote classification reliability by considering evidence from each view. Specifically, we introduce the variational Dirichlet to characterize the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory. The unified learning framework induces accurate uncertainty and accordingly endows the model with both reliability and robustness against possible noise or corruption. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.

Key facts. Cited by 168 papers in the map (data through 14 Oct 2026). Builds on 43 of its 122 references that are in the map. First posted on arXiv 25 Apr 2022.

Builds on

43 of 122 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2017On Calibration of Modern Neural Networkscited by 4,960
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  7. 2013Auto-Encoding Variational Bayescited by 4,053
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  10. 2019Contrastive Multiview Codingcited by 1,301
  11. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  12. 2016End to End Learning for Self-Driving Carscited by 1,009
31 more
  1. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  2. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  3. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  4. 2019Multimodal Transformer for Unaligned Multimodal Language Sequencescited by 645
  5. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  6. 2019What Makes Training Multi-Modal Classification Networks Hard?cited by 344
  7. 2013Black Box Variational Inferencecited by 319
  8. 2020Training independent subnetworks for robust predictioncited by 177
  9. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  10. 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
  11. 2019Ensemble Distribution Distillationcited by 158
  12. 2019Supervised Multimodal Bitransformers for Classifying Images and Textcited by 130
  13. 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
  14. 2021Evidential Deep Learning for Open Set Action Recognitioncited by 96
  15. 2021Trusted Multi-View Classificationcited by 94
  16. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 92
  17. 2020AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentationcited by 87
  18. 2019MFAS: Multimodal Fusion Architecture Searchcited by 84
  19. 2020Deep Partial Multi-View Learningcited by 71
  20. 2018Efficient Large-Scale Multi-Modal Classificationcited by 57
  21. 2020Depth Uncertainty in Neural Networkscited by 57
  22. 2016Deep Variational Canonical Correlation Analysiscited by 44
  23. 2020Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?cited by 39
  24. 2019Triplet-Based Deep Hashing Network for Cross-Modal Retrievalcited by 26
  25. 2018Uncertainty-Aware Attention for Reliable Interpretation and Predictioncited by 24
  26. 2014Majority Vote of Diverse Classifiers for Late Fusioncited by 23
  27. 2019Translate-to-Recognize Networks for RGB-D Scene Recognitioncited by 20
  28. 2021Cooperative learning for multiview analysiscited by 19
  29. 2019UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradationcited by 17
  30. 2018Learning Effective RGB-D Representations for Scene Recognitioncited by 10
  31. 2017Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classificationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 24; 2024: 50; 2025: 35; 2026: 55.

168 papers.

Sort:

By area:

  1. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 82
  2. 2023Boosting Multi-modal Model Performance with Adaptive Gradient Modulationcited by 73
  3. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  4. 2024Task-Customized Mixture of Adapters for General Image Fusioncited by 59
  5. 2024Reliable Conflictive Multi-View Learningcited by 45
  6. 2026ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrievalcited by 41
  7. 2022UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixupcited by 34
  8. 2023Deep Multiview Clustering by Contrasting Cluster Assignmentscited by 34
  9. 2024COME: Test-time adaption by Conservatively Minimizing Entropycited by 31
  10. 2022TBraTS: Trusted Brain Tumor Segmentationcited by 30
  11. 2025Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Priorcited by 29
  12. 2024Hierarchical Classification Auxiliary Network for Time Series Forecastingcited by 26
38 more
  1. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  2. 2024DOTA: Distributional Test-Time Adaptation of Vision-Language Modelscited by 23
  3. 2024Predictive Dynamic Fusioncited by 17
  4. 2024Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworkscited by 16
  5. 2025DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learningcited by 16
  6. 2023Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perceptioncited by 15
  7. 2023RedCore: Relative Advantage Aware Cross-modal Representation Learning for Missing Modalities with Imbalanced Missing Ratescited by 15
  8. 2024Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classificationcited by 15
  9. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15
  10. 2025Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approachcited by 14
  11. 2023Exploring and Exploiting Uncertainty for Incomplete Multi-View Classificationcited by 13
  12. 2023A Reliable and Interpretable Framework of Multi-view Learning for Liver Fibrosis Stagingcited by 13
  13. 2023Reliable Representation Learning for Incomplete Multi-View Missing Multi-Label Classificationcited by 12
  14. 2023DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Countingcited by 12
  15. 2024CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learningcited by 12
  16. 2024MERIT: Multi-view evidential learning for reliable and interpretable liver fibrosis stagingcited by 12
  17. 2024Balanced Multi-Relational Graph Clusteringcited by 10
  18. 2024Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Groundingcited by 10
  19. 2025Uncertainty Estimation by Flexible Evidential Deep Learningcited by 10
  20. 2023METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detectioncited by 9
  21. 2024Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspectivecited by 9
  22. 2023EviPrompt: A Training-Free Evidential Prompt Generation Method for Segment Anything Model in Medical Imagescited by 8
  23. 2024Trustworthy Multimodal Fusion for Sentiment Analysis in Ordinal Sentiment Spacecited by 8
  24. 2024Trusted Multi-view Learning under Noisy Supervisioncited by 8
  25. 2024Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cuescited by 7
  26. 2024Masked Two-channel Decoupling Framework for Incomplete Multi-view Weak Multi-label Learningcited by 7
  27. 2024TractGraphFormer: Anatomically Informed Hybrid Graph CNN-Transformer Network for Interpretable Sex and Age Prediction from Diffusion MRI Tractographycited by 7
  28. 2024Evidential Semantic Mapping in Off-road Environments with Uncertainty-aware Bayesian Kernel Inferencecited by 6
  29. 2024Evidential Deep Partial Multi-View Classification With Discount Fusioncited by 6
  30. 2024Test-Time Dynamic Image Fusioncited by 6
  31. 2022Towards Trustworthy Multi-label Sewer Defect Classification via Evidential Deep Learningcited by 5
  32. 2023Multi-View Class Incremental Learningcited by 5
  33. 2023Affective Video Content Analysis: Decade Review and New Perspectivescited by 5
  34. 2024Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classificationcited by 5
  35. 2024Confidence-aware multi-modality learning for eye disease screeningcited by 5
  36. 2024LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Datacited by 5
  37. 2022Mitigating Both Covariate and Conditional Shift for Domain Generalizationcited by 4
  38. 2023Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustnesscited by 4

50 most cited of 168 All 168 (JSON)