MTLSI-Net: A Linear Semantic Interaction Network for Parameter-Efficient Multi-Task Dense Prediction

TL;DR

MTLSI-Net introduces a linear attention-based multi-task dense prediction model that efficiently captures global cross-task interactions, achieving state-of-the-art results with reduced complexity and parameters.

Contribution

The paper proposes a novel linear attention mechanism with three key components for efficient multi-task dense prediction, reducing complexity and parameter count while maintaining high performance.

Findings

Achieves state-of-the-art performance on NYUDv2 and PASCAL-Context datasets.

Captures comprehensive cross-task interactions with linear complexity.

Reduces parameters compared to traditional self-attention models.

Abstract

Multi-task dense prediction aims to perform multiple pixel-level tasks simultaneously. However, capturing global cross-task interactions remains non-trivial due to the quadratic complexity of standard self-attention on high-resolution features. To address this limitation, we propose a Multi-Task Linear Semantic Interaction Network (MTLSI-Net), which facilitates cross-task interaction through linear attention. Specifically, MTLSI-Net incorporates three key components: a Multi-Task Multi-scale Query Linear Fusion Block, which captures cross-task dependencies across multiple scales with linear complexity using a shared global context matrix; a Semantic Token Distiller that compresses redundant features into compact semantic tokens, distilling essential cross-task knowledge; and a Cross-Window Integrated attention Block that injects global semantics into local features via a dual-branch architecture, preserving both global consistency and spatial precision. These components collectively enable the network to capture comprehensive cross-task interactions at linear complexity with reduced parameters. Extensive experiments on NYUDv2 and PASCAL-Context demonstrate that MTLSI-Net achieves state-of-the-art performance, validating its effectiveness and efficiency in multi-task learning.