A Tree-Structured Multi-Task Model Recommender
This provides a tool for researchers and practitioners in multi-task learning to efficiently generate architectures, but it is incremental as it builds on existing tree-structured methods.
The paper tackles the challenge of automatically designing tree-structured multi-task architectures for vision tasks to optimize accuracy and computation efficiency without training, achieving competitive performance on benchmarks.
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.