arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.07697stat.MLcs.LG
收藏

基于条件神经自适应过程的快速灵活多任务分类

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

University of Cambridge(剑桥大学);Invenia Labs(Invenia实验室);Google Research Berlin(谷歌研究院柏林);Microsoft Research(微软研究院)

James Requeima, Jonathan Gordon, John Bronskill, Sebastian Nowozin, Richard E. Turner

摘要:

本文的目标是设计图像分类系统,经过初始的多任务训练阶段,可以自动适应在测试时遇到的新任务。为此,我们引入了一种基于条件神经过程的方法来进行多任务分类设置,并与元学习和Few-Shot学习文献建立了联系。由此产生的方法,称为CNAPs,包括一个分类器,其参数由一个适应网络调制,该网络将当前任务的数据集作为输入。我们证明了CNAP在具有挑战性的元数据集基准上取得了最先进的结果,表明高质量的迁移学习。我们表明,该方法是强大的,避免过度拟合在低拍摄制度和下拟合在高拍摄制度。定时实验表明,CNAPs是计算效率在测试时,因为它不涉及基于梯度的适应。最后,我们表明,经过训练的模型可以立即部署到持续学习和主动学习中,在这种情况下,它们的性能优于现有的不利用迁移学习的方法。

英文摘要:

The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and establish connections to the meta-learning and few-shot learning literature. The resulting approach, called CNAPs, comprises a classifier whose parameters are modulated by an adaptation network that takes the current task's dataset as input. We demonstrate that CNAPs achieves state-of-the-art results on the challenging Meta-Dataset benchmark indicating high-quality transfer-learning. We show that the approach is robust, avoiding both over-fitting in low-shot regimes and under-fitting in high-shot regimes. Timing experiments reveal that CNAPs is computationally efficient at test-time as it does not involve gradient based adaptation. Finally, we show that trained models are immediately deployable to continual learning and active learning where they can outperform existing approaches that do not leverage transfer learning.

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。

↑