论文标题
大规模的神经结构搜索与多谐波
Large Scale Neural Architecture Search with Polyharmonic Splines
论文作者
论文摘要
神经体系结构搜索（NAS）是一种强大的工具，可以自动为许多任务（包括图像分类）设计深层神经网络。由于搜索阶段的重大计算负担，大多数NAS方法都集中在小型，平衡的数据集上。所有大规模进行NAS的尝试都使用了小的代理集，然后通过复制或堆叠搜索的单元格将学习的架构转移到较大的数据集中。我们提出了一种基于多谐波键的NAS方法，该方法可以直接进行大规模，不平衡的目标数据集执行搜索。我们证明了我们的方法对ImagEnet22k基准的有效性[16]，其中包含1400万张图像以高度不平衡的方式分布在21,841个类别上。通过探索Resnet [23]的搜索空间和直接在ImagEnet22k上的大小网络Resnext [11]体系结构，我们的多谐波键splines NAS方法设计了一个模型，该模型在Imagenet22k上获得了40.03％的TOP-1精度，绝对提高了3.13％的Art与类似的全球批量批量尺寸的3.13％。
Neural Architecture Search (NAS) is a powerful tool to automatically design deep neural networks for many tasks, including image classification. Due to the significant computational burden of the search phase, most NAS methods have focused so far on small, balanced datasets. All attempts at conducting NAS at large scale have employed small proxy sets, and then transferred the learned architectures to larger datasets by replicating or stacking the searched cells. We propose a NAS method based on polyharmonic splines that can perform search directly on large scale, imbalanced target datasets. We demonstrate the effectiveness of our method on the ImageNet22K benchmark[16], which contains 14 million images distributed in a highly imbalanced manner over 21,841 categories. By exploring the search space of the ResNet [23] and Big-Little Net ResNext [11] architectures directly on ImageNet22K, our polyharmonic splines NAS method designed a model which achieved a top-1 accuracy of 40.03% on ImageNet22K, an absolute improvement of 3.13% over the state of the art with similar global batch size [15].
