In the deep-learning community, new algorithms are published at a very fast pace. Therefore, solving an image classification problem for new datasets becomes a challenging task, as it requires to re-evaluate published algorithms and their different configurations in order to find a close to optimal classifier. To facilitate this process, before biasing our decision toward a class of neural networks or running an expensive search over the network space, we propose to estimate the classification difficulty of the dataset. Our method computes a single number that characterizes the dataset difficulty 97×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$97\times $$\end{document} faster than training state-of-the-art networks. The proposed method can be used in combination with network topology and hyper-parameter search optimizers to efficiently drive the search toward promising neural network configurations.

中文翻译：

---

用于预测深度学习精度的高效图像数据集分类难度估计

在深度学习社区，新算法的发布速度非常快。因此，解决新数据集的图像分类问题成为一项具有挑战性的任务，因为它需要重新评估已发布的算法及其不同的配置，以找到接近最优的分类器。为了促进这一过程，在将我们的决定偏向于一类神经网络或在网络空间上运行昂贵的搜索之前，我们建议估计数据集的分类难度。我们的方法计算表征数据集难度的单个数字 97×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs } \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$97\times $$\end{document} 比训练最先进的网络快。所提出的方法可以与网络拓扑和超参数搜索优化器结合使用，以有效地推动搜索朝着有希望的神经网络配置方向发展。