论文标题
depisets抗分配变化的稳健性
Robustness of Epinets against Distributional Shifts
论文作者
论文摘要
最近的工作引入了该日期，作为深度学习中不确定性建模的新方法。 Epinet是一个添加到传统神经网络中的小神经网络，它可以共同产生预测分布。尤其是，使用Epatet可以大大提高多个输入之间的联合预测的质量，这是神经网络知道其不知道的内容的量度。在本文中，我们检查了在分配变化下是否可以提供类似的优势。我们发现，在ImageNet-A/O/C中，eptets通常改善了稳健性指标。此外，这些改进比非常大的合奏所提供的改进要比计算成本降低。但是，与分配稳定深度学习的杰出问题相比，这些改进相对较小。 Epinets可能是工具箱中的有用工具，但它们远非完整的解决方案。
Recent work introduced the epinet as a new approach to uncertainty modeling in deep learning. An epinet is a small neural network added to traditional neural networks, which, together, can produce predictive distributions. In particular, using an epinet can greatly improve the quality of joint predictions across multiple inputs, a measure of how well a neural network knows what it does not know. In this paper, we examine whether epinets can offer similar advantages under distributional shifts. We find that, across ImageNet-A/O/C, epinets generally improve robustness metrics. Moreover, these improvements are more significant than those afforded by even very large ensembles at orders of magnitude lower computational costs. However, these improvements are relatively small compared to the outstanding issues in distributionally-robust deep learning. Epinets may be a useful tool in the toolbox, but they are far from the complete solution.
