# Salient Slices: Improved Neural Network Training and Performance with Image Entropy

arXiv: https://arxiv.org/abs/1907.12436 · HTML: https://mlsanity.com/paper/1907.12436/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2019.

## Built on by (most cited first, 2 of 2)

- [The Work of Art in an Age of Mechanical Generation](https://mlsanity.com/paper/2101.11587/) (2021)
- [Deep Learning in Mild Cognitive Impairment Diagnosis using Eye Movements and Image Content in Visual Memory Tasks](https://mlsanity.com/paper/2506.23016/) (2025)

## Abstract (arXiv)

As a training and analysis strategy for convolutional neural networks (CNNs), we slice images into tiled segments and use, for training and prediction, segments that both satisfy a criterion of information diversity and contain sufficient content to support classification. In particular, we utilize image entropy as the diversity criterion. This ensures that each tile carries as much information diversity as the original image, and for many applications serves as an indicator of usefulness in classification. To make predictions, a probability aggregation framework is applied to probabilities assigned by the CNN to the input image tiles. This technique facilitates the use of large, high-resolution images that would be impractical to analyze unmodified; provides data augmentation for training, which is particularly valuable when image availability is limited; and the ensemble nature of the input for prediction enhances its accuracy.