Which Tasks Should Be Learned Together in Multi-task Learning?
This addresses the challenge of optimizing task selection for real-time computer vision applications, offering a practical trade-off between time and accuracy, though it is incremental as it builds on existing multi-task learning methods.
The paper tackles the problem of task competition in multi-task learning, which often leads to inferior performance, by proposing a framework that assigns cooperating tasks to the same neural network and competing tasks to different ones, resulting in better accuracy with less inference time than both a single multi-task network and many single-task networks.
Many computer vision applications require solving multiple tasks in real-time. A neural network can be trained to solve multiple tasks simultaneously using multi-task learning. This can save computation at inference time as only a single network needs to be evaluated. Unfortunately, this often leads to inferior overall performance as task objectives can compete, which consequently poses the question: which tasks should and should not be learned together in one network when employing multi-task learning? We study task cooperation and competition in several different learning settings and propose a framework for assigning tasks to a few neural networks such that cooperating tasks are computed by the same neural network, while competing tasks are computed by different networks. Our framework offers a time-accuracy trade-off and can produce better accuracy using less inference time than not only a single large multi-task neural network but also many single-task networks.