论文标题
Mixpath：一种统一的单发神经架构搜索方法
MixPath: A Unified Approach for One-shot Neural Architecture Search
论文作者
论文摘要
在神经体系结构设计中，将多种卷积内核混合被证明是有利的。但是，当前的两阶段神经体系结构搜索方法主要限于单路搜索空间。如何有效地搜索多路径结构仍然是一个困难的问题。在本文中，我们有动力训练一击多路径超级网，以准确评估候选体系结构。具体而言，我们发现在研究的搜索空间中，从多个路径总结的特征向量几乎是单个路径的倍数。这样的差异使超级网训练及其排名能力。因此，我们提出了一种称为Shadow Batch归一化（SBN）的新型机制，以使不同特征统计量化。广泛的实验证明，SBN能够稳定优化和改善排名绩效。我们称我们的统一的多路一击方法为MixPath，该方法生成了一系列在ImageNet上获得最新结果的模型。
Blending multiple convolutional kernels is proved advantageous in neural architecture design. However, current two-stage neural architecture search methods are mainly limited to single-path search spaces. How to efficiently search models of multi-path structures remains a difficult problem. In this paper, we are motivated to train a one-shot multi-path supernet to accurately evaluate the candidate architectures. Specifically, we discover that in the studied search spaces, feature vectors summed from multiple paths are nearly multiples of those from a single path. Such disparity perturbs the supernet training and its ranking ability. Therefore, we propose a novel mechanism called Shadow Batch Normalization (SBN) to regularize the disparate feature statistics. Extensive experiments prove that SBNs are capable of stabilizing the optimization and improving ranking performance. 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.
