EUVIMEDEUVIMED entdecken
Crossref

TDSS: Task Dynamic-Synergistic Skill Adaptation for Boosting Efficient and Scalable Multi-Task Learning in Dense Visual Prediction

Haiming Yao, Qiyu Chen, Wei Luo, Zheng Zhang, Jianxing Liao, Wei You

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (14) · 11857-11865

DOI: 10.1609/aaai.v40i14.38172 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Haiming Yao und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The transfer of knowledge from large-scale pre-trained models to diverse downstream tasks has achieved remarkable success. Beyond the traditional full fine-tuning paradigm, Parameter-Efficient Fine-Tuning (PEFT) has emerged as a more efficient model adaptation approach. However, applying existing PEFT methods to adapt dense vision models, particularly in multi-task settings, remains inadequately explored due to their low efficiency, limited task scalability, and neglect of cross-task fine-tuning interactions. To address these challenges, we propose the Task Dynamic-Synergistic Skill Adaptation, termed TDSS, an efficient and scalable multi-task model adaptation framework for dense visual predictions. TDSS comprises two key components: Task-Dynamic Skill Adapters (TDSA) and Task-Synergistic Adaptation Interaction (TSAI). Specifically, TDSA are inserted in parallel into pre-trained vision models to extract task-specific adapted features through the construction of skill representation experts and task dynamic gating. TSAI is developed to enhance cross-task adaptation interaction by bridging global generic and task-specific adapted features. Extensive experiments on multi-task dense visual predictions demonstrate that TDSS surpasses existing state-of-the-art parameter-efficient fine-tuning methods, while exhibiting remarkable efficiency and scalability in parameters and computational complexity.

Zitieren

APA

Yao, H., Chen, Q., Luo, W., Zhang, Z., Liao, J., & You, W. (2026). TDSS: Task Dynamic-Synergistic Skill Adaptation for Boosting Efficient and Scalable Multi-Task Learning in Dense Visual Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(14), 11857-11865. https://doi.org/10.1609/aaai.v40i14.38172

Vancouver

Yao H, Chen Q, Luo W, Zhang Z, Liao J, You W. TDSS: Task Dynamic-Synergistic Skill Adaptation for Boosting Efficient and Scalable Multi-Task Learning in Dense Visual Prediction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(14):11857-11865. doi:10.1609/aaai.v40i14.38172

BibTeX
@article{Yao2026,
  author = {Yao, Haiming and Chen, Qiyu and Luo, Wei and Zhang, Zheng and Liao, Jianxing and You, Wei},
  title = {TDSS: Task Dynamic-Synergistic Skill Adaptation for Boosting Efficient and Scalable Multi-Task Learning in Dense Visual Prediction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {14},
  pages = {11857--11865},
  doi = {10.1609/aaai.v40i14.38172}
}
Kostenlos starten →