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

Document detail

ID

oai:arXiv.org:2407.02228

Topic

Computer Science - Computer Vision... Computer Science - Artificial Inte...

Author

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

Year

2024

listing date

7/17/2024

Keywords

scene understanding computer mamba multi-task dense

Metrics

Abstract

Multi-task dense scene understanding, which learns a model for multiple dense prediction tasks, has a wide range of application scenarios.

Modeling long-range dependency and enhancing cross-task interactions are crucial to multi-task dense prediction.

In this paper, we propose MTMamba, a novel Mamba-based architecture for multi-task scene understanding.

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 Mamba, while CTM explicitly models task interactions to facilitate information exchange across tasks.

Experiments on NYUDv2 and PASCAL-Context datasets demonstrate the superior performance of MTMamba over Transformer-based and CNN-based methods.

Notably, on the PASCAL-Context dataset, MTMamba achieves improvements of +2.08, +5.01, and +4.90 over the previous best methods in the tasks of semantic segmentation, human parsing, and object boundary detection, respectively.

The code is available at https://github.com/EnVision-Research/MTMamba.

;Comment: ECCV 2024

Lin, Baijiong,Jiang, Weisen,Chen, Pengguang,Zhang, Yu,Liu, Shu,Chen, Ying-Cong, 2024, MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders