EUVIMEDEUVIMED entdecken
Crossref

SMamba: Sparse Mamba for Event-based Object Detection

Nan Yang, Yang Wang, Zhanwen Liu, Meng Li, Yisheng An, Xiangmo Zhao

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (9) · 9229-9237

DOI: 10.1609/aaai.v39i9.32999 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Nan Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to high computational overhead. To mitigate computation cost, some researchers propose window attention based sparsification strategies to discard unimportant regions, which sacrifices the global modeling ability and results in suboptimal performance. To achieve better trade-off between accuracy and efficiency, we propose Sparse Mamba (SMamba), which performs adaptive sparsification to reduce computational effort while maintaining global modeling capability. Specifically, a Spatio-Temporal Continuity Assessment module is proposed to measure the information content of tokens and discard uninformative ones by leveraging the spatiotemporal distribution differences between activity and noise events. Based on the assessment results, an Information-Prioritized Local Scan strategy is designed to shorten the scan distance between high-information tokens, facilitating interactions among them in the spatial dimension. Furthermore, to extend the global interaction from 2D space to 3D representations, a Global Channel Interaction module is proposed to aggregate channel information from a global spatial perspective. Results on three datasets (Gen1, 1Mpx, and eTram) demonstrate that our model outperforms other methods in both performance and efficiency.

Zitieren

APA

Yang, N., Wang, Y., Liu, Z., Li, M., An, Y., & Zhao, X. (2025). SMamba: Sparse Mamba for Event-based Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(9), 9229-9237. https://doi.org/10.1609/aaai.v39i9.32999

Vancouver

Yang N, Wang Y, Liu Z, Li M, An Y, Zhao X. SMamba: Sparse Mamba for Event-based Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(9):9229-9237. doi:10.1609/aaai.v39i9.32999

BibTeX
@article{Yang2025,
  author = {Yang, Nan and Wang, Yang and Liu, Zhanwen and Li, Meng and An, Yisheng and Zhao, Xiangmo},
  title = {SMamba: Sparse Mamba for Event-based Object Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {9},
  pages = {9229--9237},
  doi = {10.1609/aaai.v39i9.32999}
}
Kostenlos starten →