Multi-task learning is central to many real-world applications. Unfortunately, obtaining labelled data for all tasks is time-consuming, challenging, and expensive. Active Learning (AL) can be used to reduce this burden. Existing techniques typically involve picking images to be annotated and providing annotations for all tasks. In this paper, we show that it is more effective to select not only the images to be annotated but also a subset of tasks for which to provide annotations at each AL iteration. Furthermore, the annotations that are provided can be used to guess pseudo-labels for the tasks that remain unannotated. We demonstrate the effectiveness of our approach on several popular multi-task datasets.
翻译:多任务学习是许多现实世界应用的核心。 不幸的是,获得所有任务的标签数据耗费时间、挑战性和昂贵。 积极学习(AL)可以用来减轻这一负担。 现有技术通常包括采集附加说明的图像,并为所有任务提供说明。 在本文中,我们显示,不仅选择附加说明的图像,而且选择每串任务提供说明,不仅更为有效。 此外,所提供的说明可用于猜测未加说明的任务的假标签。 我们展示了我们在若干广受欢迎的多任务数据集上的做法的有效性。