Cross-Task Affinity Learning for Multitask Dense Scene Predictions
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913572271947776 |
|---|---|
| author | Sinodinos, Dimitrios Armanfard, Narges |
| author_facet | Sinodinos, Dimitrios Armanfard, Narges |
| contents | Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have significantly improved multitask performance by refining task predictions using features from related tasks. However, most refinement methods struggle to efficiently capture both local and long-range dependencies between task-specific representations and cross-task patterns. In this paper, we introduce the Cross-Task Affinity Learning (CTAL) module, a lightweight framework that enhances task refinement in multitask networks. CTAL effectively captures local and long-range cross-task interactions by optimizing task affinity matrices for parameter-efficient grouped convolutions without concern for information loss. Our results demonstrate state-of-the-art MTL performance for both CNN and transformer backbones, using significantly fewer parameters than single-task learning. Our code is publicly available at https://github.com/Armanfard-Lab/EMA-Net. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11124 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Task Affinity Learning for Multitask Dense Scene Predictions Sinodinos, Dimitrios Armanfard, Narges Computer Vision and Pattern Recognition Machine Learning Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have significantly improved multitask performance by refining task predictions using features from related tasks. However, most refinement methods struggle to efficiently capture both local and long-range dependencies between task-specific representations and cross-task patterns. In this paper, we introduce the Cross-Task Affinity Learning (CTAL) module, a lightweight framework that enhances task refinement in multitask networks. CTAL effectively captures local and long-range cross-task interactions by optimizing task affinity matrices for parameter-efficient grouped convolutions without concern for information loss. Our results demonstrate state-of-the-art MTL performance for both CNN and transformer backbones, using significantly fewer parameters than single-task learning. Our code is publicly available at https://github.com/Armanfard-Lab/EMA-Net. |
| title | Cross-Task Affinity Learning for Multitask Dense Scene Predictions |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.11124 |