Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 536

The DOI matches its Crossref record; 77 of the 77 references it cites were found in a registry or an index.

Trusted Multi-View Classification With Dynamic Evidential Fusion

Open access
Han, Zongbo, Zhang, Changqing, Fu, Huazhu, Zhou, Joey Tianyi·2023·IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2022.3171983

Cites

77 of 77 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 77 references

Research works printed but not linked: 32

  1. 10.1145/3474085.3475379 · doi:10.1145/3474085.3475379
  2. Zhang, 2019, CPM-Nets: Cross partial multi-view networks, 559
  3. Liu, 2021, One pass late fusion multi-view clustering, 6850
  4. Peng, 2019, Comic: Multi-view clustering without parameter selection, 5092
  5. Simonyan, 2014, Two-stream convolutional networks for action recognition in videos, 568
  6. 10.5555/2986459.2986721 · doi:10.5555/2986459.2986721
  7. Ranganath, 2014, Black box variational inference, 814
  8. Blundell, 2015, Weight uncertainty in neural network, 1613
  9. 10.5555/3045390.3045502 · doi:10.5555/3045390.3045502
  10. Lakshminarayanan, 2017, Simple and scalable predictive uncertainty estimation using deep ensembles, 6402
  11. Sensoy, 2018, Evidential deep learning to quantify classification uncertainty, 3179
  12. Han, 2021, Trusted multi-view classification, 1
  13. Andrew, 2013, Deep canonical correlation analysis, 1247
  14. Wang, 2015, On deep multi-view representation learning, 1083
  15. Bachman, 2019, Learning representations by maximizing mutual information across views, 15535
  16. Chen, 2020, A simple framework for contrastive learning of visual representations, 1597
  17. Hassani, 2020, Contrastive multi-view representation learning on graphs, 4116
  18. 10.1109/TNNLS.2021.3117403 · doi:10.1109/tnnls.2021.3117403
  19. 10.1109/TMM.2021.3136094 · doi:10.1109/tmm.2021.3136094
  20. Denker, 1991, Transforming neural-net output levels to probability distributions, 853
  21. Havasi, 2021, Training independent subnetworks for robust prediction, 1
  22. Antorán, 2020, Depth uncertainty in neural networks
  23. Malinin, 2020, Ensemble distribution distillation
  24. Kopetzki, 2021, Evaluating robustness of predictive uncertainty estimation: Are dirichlet-based models reliable?, 5707
  25. Jøsang, 2012, Interpretation and fusion of hyper opinions in subjective logic, 1225
  26. 10.1016/0167-8655(96)00039-6 · doi:10.1016/0167-8655(96)00039-6
  27. Moon, 2020, Confidence-aware learning for deep neural networks, 7034
  28. Malinin, 2018, Predictive uncertainty estimation via prior networks, Proc. Adv. Neural Inf. Process. Syst., 31, 1
  29. Charpentier, 2020, Posterior network: Uncertainty estimation without ood samples via density-based pseudo-counts, 1356
  30. Higgins, 2017, Beta-VAE: Learning basic visual concepts with a constrained variational framework, 1
  31. Heo, 2018, Uncertainty-aware attention for reliable interpretation and prediction, 909
  32. Ayub, 2020, Centroid based concept learning for RGB-D indoor scene classification, 1

Cited by

See all 536

Metadata

Authors
Han, Z., Zhang, C., Fu, H., & Zhou, J. T.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2023-02-01
Volume
45
Issue
2
Pages
2551-2566
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W4224926219
Cited by
536
References
77
FWCI
29.22
Type
journal article
Language
en
Open access
green
Funders
  • National Key Research and Development Program of China (2019YFB2101900)
  • National Natural Science Foundation of China (61976151, 61925602, 61732011)
  • A*STAR AI3 HTPO Seed Fund (C211118012)
  • Joey Tianyi Zhou's A*STAR SERCCentral Research Fund
  • AME Programmatic Funding Scheme (A18A1b0045)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Trusted Multi-View Classification With Dynamic Evidential Fusion. https://app.cochat.ai/papers/10.1109/tpami.2022.3171983
The paper
Han, Z., Zhang, C., Fu, H., & Zhou, J. T. (2023). Trusted Multi-View Classification With Dynamic Evidential Fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2022.3171983

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.