mlsanityData to 7 Oct 2026

Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture

arXiv 2210.02676 ↗First posted 6 Oct 2022cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Uncertainty estimation is essential to make neural networks trustworthy in real-world applications. Extensive research efforts have been made to quantify and reduce predictive uncertainty. However, most existing works are designed for unimodal data, whereas multi-view uncertainty estimation has not been sufficiently investigated. Therefore, we propose a new multi-view classification framework for better uncertainty estimation and out-of-domain sample detection, where we associate each view with an uncertainty-aware classifier and combine the predictions of all the views in a principled way. The experimental results with real-world datasets demonstrate that our proposed approach is an accurate, reliable, and well-calibrated classifier, which predominantly outperforms the multi-view baselines tested in terms of expected calibration error, robustness to noise, and accuracy for the in-domain sample classification and the out-of-domain sample detection tasks.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 38 of its 70 references that are in the map. First posted on arXiv 6 Oct 2022.

Builds on

38 of 70 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  7. 2016Variational Inference: A Review for Statisticianscited by 1,466
  8. 2019Contrastive Multiview Codingcited by 1,297
  9. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  10. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  11. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,004
  12. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
26 more
  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  3. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  4. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  5. 2013Gaussian Processes for Big Datacited by 377
  6. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 368
  7. 2019What Makes Training Multi-Modal Classification Networks Hard?cited by 340
  8. 2014Scalable Variational Gaussian Process Classificationcited by 226
  9. 2018When Gaussian Process Meets Big Data: A Review of Scalable GPscited by 205
  10. 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
  11. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  12. 2021What Makes Multi-modal Learning Better than Single (Provably)cited by 151
  13. 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
  14. 2016GPflow: A Gaussian process library using TensorFlowcited by 139
  15. 2021Trusted Multi-View Classificationcited by 94
  16. 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
  17. 2018Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detectioncited by 82
  18. 2014Generalized Product of Experts for Automatic and Principled Fusion of Gaussian Process Predictionscited by 66
  19. 2018Dirichlet-based Gaussian Processes for Large-scale Calibrated Classificationcited by 50
  20. 2017Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networkscited by 48
  21. 2018Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality Controlcited by 39
  22. 2021Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributionscited by 39
  23. 2019Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classificationcited by 36
  24. 2020Estimating Model Uncertainty of Neural Networks in Sparse Information Formcited by 31
  25. 2020Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Recordscited by 16
  26. 2020Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertaintiescited by 5

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 5; 2025: 2.

10 papers.

  1. 2024Multimodal Fusion on Low-quality Data: A Comprehensive Surveycited by 48
  2. 2024Reliable Conflictive Multi-View Learningcited by 45
  3. 2023NPCL: Neural Processes for Uncertainty-Aware Continual Learningcited by 14
  4. 2023Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimationcited by 11
  5. 2025Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Modelscited by 9
  6. 2024LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Datacited by 5
  7. 2024Navigating Conflicting Views: Harnessing Trust for Learningcited by 4
  8. 2024Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusioncited by 4
  9. 2023Reliable Multimodality Eye Disease Screening via Mixture of Student's t Distributionscited by 1
  10. 2025Uncertainty-Aware Prototype Semantic Decoupling for Text-Based Person Search in Full Imagescited by 1