论文标题
DeepCore：深度学习中核心选择的综合图书馆
DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning
论文作者
论文摘要
旨在选择最有用的培训样本的子集的CoreSet选择是一个长期存在的学习问题，可以使许多下游任务（例如数据效率学习，持续学习，神经架构搜索，主动学习等）受益。但是，许多现有的核心选择方法并未为深度学习而设计，这些方法可能具有很高的复杂性和差的性能。此外，最近提出的方法在模型，数据集和不同复杂性的设置上进行评估。为了促进深度学习中核心选择的研究，我们贡献了一个全面的代码库，即深核，并就CIFAR10和ImageNet数据集的流行核心选择方法提供了经验研究。在CIFAR10和Imagenet数据集上进行的广泛实验验证了，尽管各种方法在某些实验设置中具有优势，但随机选择仍然是一个强大的基线。
Coreset selection, which aims to select a subset of the most informative training samples, is a long-standing learning problem that can benefit many downstream tasks such as data-efficient learning, continual learning, neural architecture search, active learning, etc. However, many existing coreset selection methods are not designed for deep learning, which may have high complexity and poor generalization performance. In addition, the recently proposed methods are evaluated on models, datasets, and settings of different complexities. To advance the research of coreset selection in deep learning, we contribute a comprehensive code library, namely DeepCore, and provide an empirical study on popular coreset selection methods on CIFAR10 and ImageNet datasets. Extensive experiments on CIFAR10 and ImageNet datasets verify that, although various methods have advantages in certain experiment settings, random selection is still a strong baseline.
