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.
CITATION STYLE
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
Mendeley helps you to discover research relevant for your work.