论文标题
Autoclint：2019年AutoCV挑战赛的获胜方法
AutoCLINT: The Winning Method in AutoCV Challenge 2019
论文作者
论文摘要
Neurips 2019 AutoDL Challenge是一系列六项自动化机器学习比赛。特别是，AutoCV挑战主要集中在视觉域上的分类任务上。在本文中，我们介绍了比赛中的获胜方法。所提出的方法实现了一种自主培训策略，包括有效的代码优化，并应用了自动数据增强以实现预验证的网络的快速适应。我们实施快速自动仪的轻型版本，以有效地搜索数据增强策略，以适用于任意给定的图像域。我们还经验分析了所提出的方法的组成部分，并提供了针对AutoCV数据集的消融研究。
NeurIPS 2019 AutoDL challenge is a series of six automated machine learning competitions. Particularly, AutoCV challenges mainly focused on classification tasks on visual domain. In this paper, we introduce the winning method in the competition, AutoCLINT. The proposed method implements an autonomous training strategy, including efficient code optimization, and applies an automated data augmentation to achieve the fast adaptation of pretrained networks. We implement a light version of Fast AutoAugment to search for data augmentation policies efficiently for the arbitrarily given image domains. We also empirically analyze the components of the proposed method and provide ablation studies focusing on AutoCV datasets.
