Blending multiple convolutional kernels is proved advantageous in neural architectural design. However, current neural architecture search approaches are mainly limited to stacked single-path search space. How can the one-shot doctrine search for multi-path models remains unresolved. Specifically, we are motivated to train a multi-path supernet to accurately evaluate the candidate architectures. In this paper, we discover that in the studied search space, feature vectors summed from multiple paths are nearly multiples of those from a single path, which perturbs supernet training and its ranking ability. In this regard, we propose a novel mechanism called Shadow Batch Normalization(SBN) to regularize the disparate feature statistics. Extensive experiments prove that SBN is capable of stabilizing the training and improving the ranking performance (e.g. Kendall Tau 0.597 tested on NAS-Bench-101). We call our unified multi-path one-shot approach as MixPath, which generates a series of models that achieve state-of-the-art results on ImageNet.

中文翻译：

---

MixPath：一次性神经架构搜索的统一方法

混合多个卷积核在神经架构设计中被证明是有利的。然而，当前的神经架构搜索方法主要限于堆叠的单路径搜索空间。多路径模型的一次性学说搜索如何仍未解决。具体来说，我们有动力训练一个多路径超网来准确评估候选架构。在本文中，我们发现在研究的搜索空间中，从多条路径求和的特征向量几乎是单条路径的特征向量的倍数，这扰乱了超网训练及其排序能力。在这方面，我们提出了一种称为Shadow Batch Normalization（SBN）的新机制来规范不同的特征统计。大量实验证明，SBN 能够稳定训练并提高排名性能（例如在 NAS-Bench-101 上测试的 Kendall Tau 0.597）。我们将统一的多路径一次性方法称为 MixPath，它生成一系列模型，在 ImageNet 上实现最先进的结果。