EUVIMEDEUVIMED entdecken
Crossref

MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders

Baijiong Lin, Weisen Jiang, Pengguang Chen, Shu Liu, Ying-Cong Chen

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-11 · 47 (11) · 10633-10645

DOI: 10.1109/tpami.2025.3593621 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-11. Verfasst von Baijiong Lin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Guangzhou-HKUST(GZ) Joint Funding Scheme, Guangdong Provincial Key Lab of Integrated Communication, Sensing and Computation for Ubiquitous Internet of Things.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-task dense scene understanding, which trains a model for multiple dense prediction tasks, has a wide range of application scenarios. Capturing long-range dependency and enhancing cross-task interactions are crucial to multi-task dense prediction. In this paper, we propose MTMamba++, a novel architecture for multi-task scene understanding featuring with a Mamba-based decoder. It contains two types of core blocks: self-task Mamba (STM) block and cross-task Mamba (CTM) block. STM handles long-range dependency by leveraging state-space models, while CTM explicitly models task interactions to facilitate information exchange across tasks. We design two types of CTM block, namely F-CTM and S-CTM, to enhance cross-task interaction from feature and semantic perspectives, respectively. Extensive experiments on NYUDv2, PASCAL-Context, and Cityscapes datasets demonstrate the superior performance of MTMamba++ over CNN-based, Transformer-based, and diffusion-based methods while maintaining high computational efficiency.

Förderung

  • Guangzhou-HKUST(GZ) Joint Funding Scheme
  • Guangdong Provincial Key Lab of Integrated Communication, Sensing and Computation for Ubiquitous Internet of Things

Zitieren

APA

Lin, B., Jiang, W., Chen, P., Liu, S., & Chen, Y. C. (2025). MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(11), 10633-10645. https://doi.org/10.1109/tpami.2025.3593621

Vancouver

Lin B, Jiang W, Chen P, Liu S, Chen YC. MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(11):10633-10645. doi:10.1109/tpami.2025.3593621

BibTeX
@article{Lin2025,
  author = {Lin, Baijiong and Jiang, Weisen and Chen, Pengguang and Liu, Shu and Chen, Ying-Cong},
  title = {MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {11},
  pages = {10633--10645},
  doi = {10.1109/tpami.2025.3593621}
}
Kostenlos starten →