Efficient image dataset classification difficulty estimation for predicting deep-learning accuracy

20Citations
Citations of this article
58Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

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 × 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.

Cite

CITATION STYLE

APA

Scheidegger, F., Istrate, R., Mariani, G., Benini, L., Bekas, C., & Malossi, C. (2021). Efficient image dataset classification difficulty estimation for predicting deep-learning accuracy. Visual Computer, 37(6), 1593–1610. https://doi.org/10.1007/s00371-020-01922-5

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free