Understanding the inter-relations and interactions between tasks is crucial for multi-task dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this work, we introduce a novel decoder-based framework, Parameter Aware Mamba Model (PAMM), specifically designed for dense prediction in multi-task learning setting. Distinct from approaches that employ Transformers to model holistic task relationships, PAMM leverages the rich, scalable parameters of state space models to enhance task interconnectivity. It features dual state space parameter experts that integrate and set task-specific parameter priors, capturing the intrinsic properties of each task. This approach not only facilitates precise multi-task interactions but also allows for the global integration of task priors through the structured state space sequence model (S4). Furthermore, we employ the Multi-Directional Hilbert Scanning method to construct multi-angle feature sequences, thereby enhancing the sequence model's perceptual capabilities for 2D data. Extensive experiments on the NYUD-v2 and PASCAL-Context benchmarks demonstrate the effectiveness of our proposed method. Our code is available at https://github.com/CQC-gogopro/PAMM.

翻译：理解任务间的相互关联与交互对于多任务密集预测至关重要。现有方法主要利用卷积层和注意力机制来探索任务级交互。本文提出了一种新颖的基于解码器的框架——参数感知Mamba模型（PAMM），专为多任务学习环境下的密集预测而设计。与采用Transformer建模整体任务关系的方法不同，PAMM利用状态空间模型丰富且可扩展的参数来增强任务间的互联性。该模型采用双状态空间参数专家模块，通过集成并设定任务特定的参数先验，捕捉每个任务的内在特性。此方法不仅促进了精确的多任务交互，还通过结构化状态空间序列模型（S4）实现了任务先验的全局整合。此外，我们采用多方向希尔伯特扫描方法构建多角度特征序列，从而增强了序列模型对二维数据的感知能力。在NYUD-v2和PASCAL-Context基准数据集上的大量实验验证了所提方法的有效性。代码已开源：https://github.com/CQC-gogopro/PAMM。