论文标题
在世界内徘徊：在线上下文化的少数学习
Wandering Within a World: Online Contextualized Few-Shot Learning
论文作者
论文摘要
我们的目标是通过将几乎没有记录的学习的标准框架扩展到在线持续的环境中，弥合典型的人类和机器学习环境之间的差距。在这种情况下，情节没有单独的培训和测试阶段，而是在学习新颖课程时在线评估模型。就像在现实世界中一样，时空环境的存在有助于我们在过去的学习技能中检索学习的技能，我们在线的几个学习设置也具有贯穿整个时间变化的基本环境。对象类在上下文中相关联，并推断正确的上下文可以带来更好的性能。在此设置的基础上，我们根据大规模室内图像提出了一个新的几次学习数据集，该数据集模仿了一个世界中徘徊的代理商的视觉体验。此外，我们将流行的几种学习方法转换为在线版本，我们还提出了一种新的上下文原型内存模型，该模型可以利用最近过去的时空上下文信息。
We aim to bridge the gap between typical human and machine-learning environments by extending the standard framework of few-shot learning to an online, continual setting. In this setting, episodes do not have separate training and testing phases, and instead models are evaluated online while learning novel classes. As in the real world, where the presence of spatiotemporal context helps us retrieve learned skills in the past, our online few-shot learning setting also features an underlying context that changes throughout time. Object classes are correlated within a context and inferring the correct context can lead to better performance. Building upon this setting, we propose a new few-shot learning dataset based on large scale indoor imagery that mimics the visual experience of an agent wandering within a world. Furthermore, we convert popular few-shot learning approaches into online versions and we also propose a new contextual prototypical memory model that can make use of spatiotemporal contextual information from the recent past.
