Journal article · 2026 · Open access
Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization
IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18 · Published 1 January 2026 · DOI 10.1109/tpami.2026.3750284
In brief
“Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization” is a 2026 journal article by Hongzhao Li and 7 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 0 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Pattern Analysis and Machine Intelligence.
- Citations
- 0
- Authors
- 8
Abstract
Multimodal Domain Generalization (MMDG) aims to learn models that generalize to unseen domains under unpredictable, modality-dependent distribution shifts. Despite recent progress, existing methods often rely on heuristic fusion strategies and lack a unified theoretical perspective, limiting their robustness under domain shifts. In this paper, we identify three fundamental challenges in MMDG: (I) insufficient cross-domain invariance across individual modalities and cross-modal interaction subspaces; (II) instability induced by asynchronous modality degradation, through which unreliable modalities impair joint representations; and (III) limited representation diversity, which exacerbates source-target support mismatch. To characterize these challenges, we derive a generalization error bound for a stability-weighted ensemble of modality-wise hypotheses, revealing three corresponding factors: Invariance (Source-Source Divergence), Stability (Stability-Weighted Error), and Diversity (Target-Convex Hull Divergence). Guided by this analysis, we develop a unified nonlinear fusion framework comprising Multi-Granularity Adversarial Alignment to promote invariance across modality-specific, interaction, and fusion spaces, Stability-Aware Adaptive Learning to prioritize reliable modalities during source training and mitigate asynchronous degradation, and Manifold Expansion to increase normalized source-feature dispersion as a source-side regularizer. Extensive experiments on multiple benchmarks show that our framework achieves the best overall average rank across 43 transfer tasks on seven datasets spanning four task families and eight diverse modalities.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, H., Hu, S., Shen, X., Wan, H., Jiu, M., Li, S., Khan, M. H., & Xu, M. (2026). Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3750284
MLA 9
Li, Hongzhao, et al. “Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–18. https://doi.org/10.1109/tpami.2026.3750284.
Chicago
Li, Hongzhao, Shizhe Hu, Xianglong Shen, Hualei Wan, Mingyuan Jiu, Shupan Li, Muhammad Haris Khan, and Mingliang Xu. 2026. “Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–18. https://doi.org/10.1109/tpami.2026.3750284.
Harvard
Li, H. et al. (2026) ‘Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–18. doi:10.1109/tpami.2026.3750284.
IEEE
H. Li et al., “Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–18, 2026, doi: 10.1109/tpami.2026.3750284.
BibTeX
@article{li2026invariance,
title = {{Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization}},
author = {Li, Hongzhao and Hu, Shizhe and Shen, Xianglong and Wan, Hualei and Jiu, Mingyuan and Li, Shupan and Khan, Muhammad Haris and Xu, Mingliang},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {PP},
pages = {1--18},
doi = {10.1109/tpami.2026.3750284},
url = {https://doi.org/10.1109/tpami.2026.3750284}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- domain shift
- generalization bounds
- ensemble stability
- representation diversity
- nonlinear fusion
- adversarial alignment
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Li, H., Hu, S., Shen, X., Wan, H., Jiu, M., Li, S., Khan, M. H., & Xu, M. (2026). Invariance, Stability, and Diversity: A Unified Framework for Multimodal Domain Generalization. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3750284
How many times has this paper been cited?
0 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE Transactions on Pattern Analysis and Machine Intelligence: sign in and open the full text from this page.
Who wrote this paper?
Hongzhao Li, Shizhe Hu, Xianglong Shen, Hualei Wan, Mingyuan Jiu, Shupan Li, Muhammad Haris Khan, Mingliang Xu.
What is the DOI of this paper?
10.1109/tpami.2026.3750284, permanently at https://doi.org/10.1109/tpami.2026.3750284. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.