In recent years, zero-cost proxies are gaining ground in neural architecture
search (NAS). These methods allow finding the optimal neural network for a
given task faster and with a lesser computational load than conventional NAS
methods. Equally important is the fact that they also she
在这篇文章中,我们提出了一种新颖的轻量级鲁棒性零成本代理,该代理考虑了初始化状态下干净和扰动图像的特征、参数和梯度的一致性,从而实现了能够学习在多种扰动情况下显示出鲁棒性的神经结构的高效快速搜索。 针对多个基准数据集和不同搜索空间,我们的代理能够快速有效地搜索出一致鲁棒的神经结构,大大优于现有的基于清晰无注入 NAS 和基于注入 NAS 减少的搜索成本。