论文标题
树结构的多任务模型推荐
A Tree-Structured Multi-Task Model Recommender
论文作者
论文摘要
在多任务学习（MTL）的背景下，已经采用了树结构的多任务架构来共同处理多个视觉任务。主要的挑战是确定给定骨干模型的每个任务分支在哪里分支，以优化任务准确性和计算效率。为了应对挑战，本文提出了一个建议，鉴于一组任务和基于卷积神经网络的骨干模型，自动提出了树结构的多任务架构，这些多任务体系结构可以实现较高的任务性能，同时在不执行模型培训的情况下满足用户指定的计算预算。对流行MTL基准测试的广泛评估表明，与最先进的MTL方法相比，推荐的架构可以实现竞争性的任务准确性和计算效率。我们的树结构化多任务模型推荐使用者是开源的，可在https://github.com/zhanglijun95/treemtl上找到。
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.
