A Tree-Structured Multi-Task Model Recommender
Abstract
Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL). The major challenge is to determine where to branch out for each task given a backbone model to optimize for both task accuracy and computation efficiency. To address the challenge, this paper proposes a recommender that, given a set of tasks and a convolutional neural network-based backbone model, automatically suggests tree-structured multi-task architectures that could achieve a high task performance while meeting a user-specified computation budget without performing model training. Extensive evaluations on popular MTL benchmarks show that the recommended architectures could achieve competitive task accuracy and computation efficiency compared with state-of-the-art MTL methods. Our tree-structured multi-task model recommender is open-sourced and available at https://github.com/zhanglijun95/TreeMTL.
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2022
- DOI:
- 10.48550/arXiv.2203.05092
- arXiv:
- arXiv:2203.05092
- Bibcode:
- 2022arXiv220305092Z
- Keywords:
-
- Computer Science - Machine Learning;
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- 12 pages, 2 figures