EUVIMEDEUVIMED entdecken
Crossref

MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation

Fuqiang Gu, Yuanke Li, Xianlei Long, Kangping Ji, Chao Chen, Qingyi Gu, Zhenliang Ni

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4302-4310

DOI: 10.1609/aaai.v40i6.42427 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Fuqiang Gu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages such as high temporal resolution and low latency, yet lack color and texture, making them insufficient on their own. To address this, recent research has explored multimodal fusion of RGB and event data; however, many existing approaches are computationally expensive and focus primarily on spatial fusion, neglecting the temporal dynamics inherent in event streams. In this work, we propose MambaSeg, a novel dual-branch semantic segmentation framework that employs parallel Mamba encoders to efficiently model RGB images and event streams. To reduce cross-modal ambiguity, we introduce the Dual-Dimensional Interaction Module (DDIM), comprising a Cross-Spatial Interaction Module (CSIM) and a Cross-Temporal Interaction Module (CTIM), which jointly perform fine-grained fusion along both spatial and temporal dimensions. This design improves cross-modal alignment, reduces ambiguity, and leverages the complementary properties of each modality. Extensive experiments on the DDD17 and DSEC datasets demonstrate that MambaSeg achieves state-of-the-art segmentation performance while significantly reducing computational cost, showcasing its promise for efficient, scalable, and robust multimodal perception.

Zitieren

APA

Gu, F., Li, Y., Long, X., Ji, K., Chen, C., Gu, Q., & Ni, Z. (2026). MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4302-4310. https://doi.org/10.1609/aaai.v40i6.42427

Vancouver

Gu F, Li Y, Long X, Ji K, Chen C, Gu Q, et al. MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4302-4310. doi:10.1609/aaai.v40i6.42427

BibTeX
@article{Gu2026,
  author = {Gu, Fuqiang and Li, Yuanke and Long, Xianlei and Ji, Kangping and Chen, Chao and Gu, Qingyi and Ni, Zhenliang},
  title = {MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4302--4310},
  doi = {10.1609/aaai.v40i6.42427}
}
Kostenlos starten →