Conference paper · 2025 · Open access
Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion
International Conference on Learning Representations · Published 1 May 2025 · DOI 10.48550/arxiv.2410.12592
In brief
“Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion” is a 2025 conference paper by Minkyoung Cho and 7 co-authors, published in International Conference on Learning Representations. OpenAlex counts 21 citations as of 22 November 2026, which puts it in the top 5% of works published in 2025 by citations. It is open access under a CC BY-NC-SA licence: the full text is free to read at International Conference on Learning Representations.
- Citations
- 21
- Most cited in
- 2026 (18)
- Field-weighted impact
- 3.66
- References
- 77
- Authors
- 8
Abstract
An important paradigm in 3D object detection is the use of multiple modalities to enhance accuracy in both normal and challenging conditions, particularly for long-tail scenarios. To address this, recent studies have explored two directions of adaptive approaches: MoE-based adaptive fusion, which struggles with uncertainties arising from distinct object configurations, and late fusion for output-level adaptive fusion, which relies on separate detection pipelines and limits comprehensive understanding. In this work, we introduce Cocoon, an object- and feature-level uncertainty-aware fusion framework. The key innovation lies in uncertainty quantification for heterogeneous representations, enabling fair comparison across modalities through the introduction of a feature aligner and a learnable surrogate ground truth, termed feature impression. We also define a training objective to ensure that their relationship provides a valid metric for uncertainty quantification. Cocoon consistently outperforms existing static and adaptive methods in both normal and challenging conditions, including those with natural and artificial corruptions. Furthermore, we show the validity and efficacy of our uncertainty metric across diverse datasets.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Cho, M., Cao, Y., Sun, J., Zhang, Q., Pavone, M., Park, J. J., Yang, H., & Mao, Z. M. (2025). Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion. International Conference on Learning Representations. https://doi.org/10.48550/arxiv.2410.12592
MLA 9
Cho, Minkyoung, et al. “Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion.” International Conference on Learning Representations, 2025. https://doi.org/10.48550/arxiv.2410.12592.
Chicago
Cho, Minkyoung, Yulong Cao, Jiachen Sun, Qingzhao Zhang, Marco Pavone, Jeong Joon Park, Heng Yang, and Zhuoqing Morley Mao. 2025. “Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion.” International Conference on Learning Representations. https://doi.org/10.48550/arxiv.2410.12592.
Harvard
Cho, M. et al. (2025) ‘Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion’, International Conference on Learning Representations. doi:10.48550/arxiv.2410.12592.
IEEE
M. Cho et al., “Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion,” International Conference on Learning Representations, 2025, doi: 10.48550/arxiv.2410.12592.
BibTeX
@inproceedings{cho2025cocoon,
title = {{Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion}},
author = {Cho, Minkyoung and Cao, Yulong and Sun, Jiachen and Zhang, Qingzhao and Pavone, Marco and Park, Jeong Joon and Yang, Heng and Mao, Zhuoqing Morley},
booktitle = {International Conference on Learning Representations},
year = {2025},
doi = {10.48550/arxiv.2410.12592},
url = {https://doi.org/10.48550/arxiv.2410.12592}
}
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
- 3D object detection
- multisensory perception
- uncertainty quantification
- sensor fusion
- long-tail scenarios
- data corruption
- robustness
- feature-level fusion
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?
Cho, M., Cao, Y., Sun, J., Zhang, Q., Pavone, M., Park, J. J., Yang, H., & Mao, Z. M. (2025). Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion. International Conference on Learning Representations. https://doi.org/10.48550/arxiv.2410.12592
How many times has this paper been cited?
21 times, according to OpenAlex on 22 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 International Conference on Learning Representations: sign in and open the PDF from this page.
Who wrote this paper?
Minkyoung Cho, Yulong Cao, Jiachen Sun, Qingzhao Zhang, Marco Pavone, Jeong Joon Park, Heng Yang, Zhuoqing Morley Mao.
What is the DOI of this paper?
10.48550/arxiv.2410.12592, permanently at https://doi.org/10.48550/arxiv.2410.12592. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 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.