DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning

by   Chengcheng Guo, et al.

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 ability to unseen representations. 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 experiment results show that, although some methods perform better in certain experiment settings, random selection is still a strong baseline.


page 1

page 2

page 3

page 4


Avalanche: A PyTorch Library for Deep Continual Learning

Continual learning is the problem of learning from a nonstationary strea...

ALBench: A Framework for Evaluating Active Learning in Object Detection

Active learning is an important technology for automated machine learnin...

One Pass ImageNet

We present the One Pass ImageNet (OPIN) problem, which aims to study the...

Continual Evidential Deep Learning for Out-of-Distribution Detection

Uncertainty-based deep learning models have attracted a great deal of in...

Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic Interference

In this paper we analyze the classification performance of neural networ...

On the Importance of Strong Baselines in Bayesian Deep Learning

Like all sub-fields of machine learning, Bayesian Deep Learning is drive...

Code Repositories


Code for coreset selection methods

view repo

Please sign up or login with your details

Forgot password? Click here to reset