AdaShare:学习如何共享高效的深度多任务学习
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
摘要:
多任务学习是计算机视觉中一个开放的、具有挑战性的问题。使用深度神经网络进行多任务学习的典型方式是通过共享所有初始层并在特定点分支的手工方案,或者通过具有额外特征共享/融合机制的单独任务特定网络。与现有的方法不同,我们提出了一种自适应共享方法,称为AdaShare,它决定在哪些任务中共享什么,以实现最佳的识别精度,同时考虑资源效率。具体来说,我们的主要思想是通过特定于任务的策略来学习共享模式,该策略选择性地选择在多任务网络中为给定任务执行哪些层。我们使用标准的反向传播,有效地优化了特定于任务的策略和网络权重。在几个具有挑战性和多样性的基准数据集上进行的实验,以及不同数量的任务,很好地证明了我们的方法比最先进的方法的有效性。项目页面:https://cs-people.bu.edu/sunxm/AdaShare/project.html。
英文摘要:
Multi-task learning is an open and challenging problem in computer vision. The typical way of conducting multi-task learning with deep neural networks is either through handcrafted schemes that share all initial layers and branch out at an adhoc point, or through separate task-specific networks with an additional feature sharing/fusion mechanism. Unlike existing methods, we propose an adaptive sharing approach, called AdaShare, that decides what to share across which tasks to achieve the best recognition accuracy, while taking resource efficiency into account. Specifically, our main idea is to learn the sharing pattern through a task-specific policy that selectively chooses which layers to execute for a given task in the multi-task network. We efficiently optimize the task-specific policy jointly with the network weights, using standard back-propagation. Experiments on several challenging and diverse benchmark datasets with a variable number of tasks well demonstrate the efficacy of our approach over state-of-the-art methods. Project page: https://cs-people.bu.edu/sunxm/AdaShare/project.html.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。