The performance of multi-task learning in Convolutional Neural Networks (CNNs) hinges on the design of feature sharing between tasks within the architecture. The number of possible sharing patterns are combinatorial in the depth of the network and the number of tasks, and thus hand-crafting an architecture, purely based on the human intuitions of task relationships can be time-consuming and suboptimal. In this paper, we present a probabilistic approach to learning task-specific and shared representations in CNNs for multi-task learning. Specifically, we propose "stochastic filter groups'' (SFG), a mechanism to assign convolution kernels in each layer to "specialist'' or "generalist'' groups, which are specific to or shared across different tasks, respectively. The SFG modules determine the connectivity between layers and the structures of task-specific and shared representations in the network. We employ variational inference to learn the posterior distribution over the possible grouping of kernels and network parameters. Experiments demonstrate that the proposed method generalises across multiple tasks and shows improved performance over baseline methods.

这篇文章提出了一种基于概率方法的卷积神经网络多任务学习的机制，采用“随机过滤器组”(SFG) 来确定不同任务之间卷积核的连接性并学习可能的卷积核分组和网络参数的后验分布，实验表明该方法在多任务学习上具有泛化能力和优越性能。

多任务 CNN 的随机滤波器组：学习专家和通用卷积核