Salient Slices: Improved Neural Network Training and Performance with Image Entropy
This incremental method addresses efficiency and accuracy issues in image classification for domains with limited data or high-resolution inputs.
The paper tackles the challenge of training CNNs on large, high-resolution images by slicing them into tiles selected based on image entropy for diversity, which also provides data augmentation. This approach improves prediction accuracy through probability aggregation, with reported gains in performance metrics.
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.