.png){kind=icon}
.png){kind=icon}
Return
Efficient image dataset classification difficulty estimation for predicting deep-learning accuracy
.png){kind=icon}
OA
AI
DOI：10.1007/s00371-020-01922-5.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 97x 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.
Keywords:
Dataset characterization
Classification difficulty
Deep learning
Image classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.9
Papers:
4.6K
Citations:
6.5K