MTLSI-Net: A Linear Semantic Interaction Network for Parameter-Efficient Multi-Task Dense Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914440077639680 |
|---|---|
| author | Liu, Chen Man, Hengyu Fan, Xiaopeng Zhao, Debin |
| author_facet | Liu, Chen Man, Hengyu Fan, Xiaopeng Zhao, Debin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01995 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MTLSI-Net: A Linear Semantic Interaction Network for Parameter-Efficient Multi-Task Dense Prediction Liu, Chen Man, Hengyu Fan, Xiaopeng Zhao, Debin Computer Vision and Pattern Recognition 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. |
| title | MTLSI-Net: A Linear Semantic Interaction Network for Parameter-Efficient Multi-Task Dense Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.01995 |