Le Wang, Sanping Zhou, Ye Deng, Mang Cao, Yizhe Li, Wenli Huang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Sufficient cross-task interaction is crucial for success in multi-task dense prediction. However, sufficient interaction often results in high computational complexity, forcing existing methods to face the trade-off between interaction completeness and computational efficiency. To address this limitation, this work proposes a Bidirectional Interaction Mamba (BIM), which incorporates novel scanning mechanisms to adapt the Mamba modeling approach for multitask dense prediction. On the one hand, we introduce a novel Bidirectional Interaction Scan (BI-Scan) mechanism, which constructs task-specific representations as bidirectional sequences during interaction. By integrating taskfirst and position-first scanning modes within a unified linear complexity architecture, BI-Scan efficiently preserves critical cross-task information. On the other hand, we employ a Multi-Scale Scan (MS-Scan) mechanism to achieve multi-granularity scene modeling. This design not only meets the diverse granularity requirements of various tasks but also enhances nuanced cross-task feature interactions. Extensive experiments on two challenging benchmarks, i.e., NYUD-V2 and PASCAL-Context, show the superiority of our BIM vs its state-of-the-art competitors. Codes are available online: https://github.com/mmm-cc/BIM_ for_MTL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2508.20376")
get_code_for_paper("2508.20376")
have("2508.20376")
Connect an agent — have() is free.