Journal article · 2026 · Open access

Rotation Equivariant Mamba for Vision Tasks

Zhongchen Zhao, Qi Xie, Keyu Huang, Lei Zhang, Deyu Meng, Zongben Xu

IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18 · Published 29 October 2026 · DOI 10.1109/tpami.2026.3748291

Open full textCite this paper

In brief

“Rotation Equivariant Mamba for Vision Tasks” is a 2026 journal article by Zhongchen Zhao and 5 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 1 citations as of 18 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
1
Most cited in
2026 (1)
Field-weighted impact
1.14
References
78
Authors
6

Abstract

Rotation equivariance is an important structural prior for a broad range of vision tasks, particularly in domains such as remote sensing and medical imaging where objects have no canonical orientation, yet it remains notably absent from current Mamba-based vision architectures. Despite the success of Mamba in natural language processing and its growing adoption in computer vision, existing visual Mamba models fail to account for rotational symmetry in their design. This omission renders them sensitive to image rotations, thereby constraining their robustness and cross-task generalization. To address this limitation, we incorporate rotation symmetry, an important geometric prior in many visual domains, into Mamba-based architectures. Specifically, we introduce EQ-VMamba, the first rotation equivariant visual Mamba architecture for vision tasks. The core components of EQ-VMamba include a carefully designed rotation equivariant cross-scan strategy and group Mamba blocks. Moreover, we provide a rigorous theoretical analysis of the intrinsic equivariance error, demonstrating that the proposed architecture enforces end-to-end rotation equivariance under the $\mathrm{p}4$ rotation group. Extensive experiments across multiple benchmarks-including high-level image classification, mid-level semantic segmentation, and low-level image super-resolution-demonstrate that EQ-VMamba consistently improves rotation robustness and achieves superior or competitive performance compared to non-equivariant baselines on most evaluated benchmarks, while requiring 40-70% fewer parameters. These results indicate that embedding rotation equivariance not only effectively bolsters the robustness of visual Mamba models against rotation transformations, but also improves accuracy on data exhibiting rotational symmetry, with substantially improved parameter efficiency.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zhao, Z., Xie, Q., Huang, K., Zhang, L., Meng, D., & Xu, Z. (2026). Rotation Equivariant Mamba for Vision Tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3748291

MLA 9

Zhao, Zhongchen, et al. “Rotation Equivariant Mamba for Vision Tasks.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–18. https://doi.org/10.1109/tpami.2026.3748291.

Chicago

Zhao, Zhongchen, Qi Xie, Keyu Huang, Lei Zhang, Deyu Meng, and Zongben Xu. 2026. “Rotation Equivariant Mamba for Vision Tasks.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–18. https://doi.org/10.1109/tpami.2026.3748291.

Harvard

Zhao, Z. et al. (2026) ‘Rotation Equivariant Mamba for Vision Tasks’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–18. doi:10.1109/tpami.2026.3748291.

IEEE

Z. Zhao, Q. Xie, K. Huang, L. Zhang, D. Meng, and Z. Xu, “Rotation Equivariant Mamba for Vision Tasks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–18, 2026, doi: 10.1109/tpami.2026.3748291.

BibTeX

@article{zhao2026rotation,
  title     = {{Rotation Equivariant Mamba for Vision Tasks}},
  author    = {Zhao, Zhongchen and Xie, Qi and Huang, Keyu and Zhang, Lei and Meng, Deyu and Xu, Zongben},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year      = {2026},
  volume    = {PP},
  pages     = {1--18},
  doi       = {10.1109/tpami.2026.3748291},
  url       = {https://doi.org/10.1109/tpami.2026.3748291}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • rotation equivariance
  • Mamba
  • visual state space model
  • rotational symmetry
  • image classification
  • semantic segmentation
  • image super-resolution
  • rotation robustness

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zhao, Z., Xie, Q., Huang, K., Zhang, L., Meng, D., & Xu, Z. (2026). Rotation Equivariant Mamba for Vision Tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3748291

How many times has this paper been cited?

1 times, according to OpenAlex on 18 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?

Zhongchen Zhao, Qi Xie, Keyu Huang, Lei Zhang, Deyu Meng, Zongben Xu.

What is the DOI of this paper?

10.1109/tpami.2026.3748291, permanently at https://doi.org/10.1109/tpami.2026.3748291. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 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.