mlsanityData to 14 Oct 2026

Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions

arXiv 2111.08456 ↗First posted 11 Nov 2021cs.LG cs.AIcited by 39

Not on the map. Why?

Abstract (arXiv)

Multimodal regression is a fundamental task, which integrates the information from different sources to improve the performance of follow-up applications. However, existing methods mainly focus on improving the performance and often ignore the confidence of prediction for diverse situations. In this study, we are devoted to trustworthy multimodal regression which is critical in cost-sensitive domains. To this end, we introduce a novel Mixture of Normal-Inverse Gamma distributions (MoNIG) algorithm, which efficiently estimates uncertainty in principle for adaptive integration of different modalities and produces a trustworthy regression result. Our model can be dynamically aware of uncertainty for each modality, and also robust for corrupted modalities. Furthermore, the proposed MoNIG ensures explicitly representation of (modality-specific/global) epistemic and aleatoric uncertainties, respectively. Experimental results on both synthetic and different real-world data demonstrate the effectiveness and trustworthiness of our method on various multimodal regression tasks (e.g., temperature prediction for superconductivity, relative location prediction for CT slices, and multimodal sentiment analysis).

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 28 of its 57 references that are in the map. First posted on arXiv 11 Nov 2021.

Builds on

28 of 57 references.

References · 28

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2015VQA: Visual Question Answeringcited by 2,506
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  6. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,013
  7. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  8. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  9. 2020Calibrating Deep Neural Networks using Focal Losscited by 357
  10. 2019Deep Evidential Regressioncited by 355
  11. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  12. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
16 more
  1. 2016MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videoscited by 194
  2. 2019Addressing Failure Prediction by Learning Model Confidencecited by 186
  3. 2019Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Modelscited by 178
  4. 2018Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalitiescited by 149
  5. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  6. 2021Trusted Multi-View Classificationcited by 94
  7. 2018Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviorscited by 89
  8. 2020Deep Partial Multi-View Learningcited by 71
  9. 20183D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Trainingcited by 58
  10. 2018Efficient Large-Scale Multi-Modal Classificationcited by 57
  11. 2020Depth Uncertainty in Neural Networkscited by 57
  12. 2018Multimodal Language Analysis with Recurrent Multistage Fusioncited by 44
  13. 2019Learning Representations from Imperfect Time Series Data via Tensor Rank Regularizationcited by 30
  14. 2020Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD Detectioncited by 26
  15. 2020Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensorscited by 17
  16. 2014Shared Representation Learning for Heterogeneous Face Recognitioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 13; 2025: 7; 2026: 9.

39 papers.

Sort:

  1. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 82
  2. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  3. 2024Multimodal Fusion on Low-quality Data: A Comprehensive Surveycited by 49
  4. 2023On Second-Order Scoring Rules for Epistemic Uncertainty Quantificationcited by 38
  5. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 35
  6. 2022UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixupcited by 34
  7. 2023ELFNet: Evidential Local-global Fusion for Stereo Matchingcited by 25
  8. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  9. 2024Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?cited by 18
  10. 2024Predictive Dynamic Fusioncited by 17
  11. 2024Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworkscited by 16
  12. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15
27 more
  1. 2023Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimationcited by 11
  2. 2022Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picturecited by 10
  3. 2025Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoringcited by 10
  4. 2024Trustworthy Multimodal Fusion for Sentiment Analysis in Ordinal Sentiment Spacecited by 8
  5. 2024Towards the Causal Complete Cause of Multi-Modal Representation Learningcited by 5
  6. 2023dugMatting: Decomposed-Uncertainty-Guided Mattingcited by 4
  7. 2026Evidential Neural Radiance Fieldscited by 4
  8. 2023Reweighted Mixup for Subpopulation Shiftcited by 2
  9. 2024Multi-modal MRI Translation via Evidential Regression and Distribution Calibrationcited by 2
  10. 2025Explainable Multimodal Regression via Information Decompositioncited by 2
  11. 2026Context-specific Credibility-aware Multimodal Fusion with Conditional Probabilistic Circuitscited by 2
  12. 2022Improving Uncertainty Quantification of Variance Networks by Tree-Structured Learningcited by 1
  13. 2024Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusioncited by 1
  14. 2025Robust Multimodal Sentiment Analysis of Image-Text Pairs by Distribution-Based Feature Recovery and Fusioncited by 1
  15. 2024Gaussian Mixture based Evidential Learning for Stereo Matchingcited by 0
  16. 2024Multi-QuAD: Multi-Level Quality-Adaptive Dynamic Network for Reliable Multimodal Classificationcited by 0
  17. 2025CEC-MMR: Cross-Entropy Clustering Approach to Multi-Modal Regressioncited by 0
  18. 2025UGPL: Uncertainty-Guided Progressive Learning for Evidence-Based Classification in Computed Tomographycited by 0
  19. 2025DEFNet: Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessmentcited by 0
  20. 2025Long-Term Alzheimers Disease Prediction: A Novel Image Generation Method Using Temporal Parameter Estimation with Normal Inverse Gamma Distribution on Uneven Time Seriescited by 0
  21. 2026Communication-Efficient Multi-Modal Edge Inference via Uncertainty-Aware Distributed Learningcited by 0
  22. 2026EviDep: Uncertainty-Aware Multimodal Depression Estimation via Disentangled Evidential Learningcited by 0
  23. 2026Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decodingcited by 0
  24. 2026Rethinking Gradient Modulation in Multimodal Regressioncited by 0
  25. 2026Trustworthy Protein-Ligand Binding Affinity Prediction via Reliability-Aware Multi-Engine Fusioncited by 0
  26. 2026Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusioncited by 0
  27. 2026SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosiscited by 0