Context Augmentation for Convolutional Neural Networks
This work addresses the problem of limited data availability for image classification tasks, offering a practical augmentation method, though it appears incremental in nature.
The study investigated how background changes in training datasets affect convolutional neural network testing accuracies for image classification, finding drastic effects, and enhanced existing augmentation techniques with foreground segmented objects to improve accuracy with small datasets.
Recent enhancements of deep convolutional neural networks (ConvNets) empowered by enormous amounts of labeled data have closed the gap with human performance for many object recognition tasks. These impressive results have generated interest in understanding and visualization of ConvNets. In this work, we study the effect of background in the task of image classification. Our results show that changing the backgrounds of the training datasets can have drastic effects on testing accuracies. Furthermore, we enhance existing augmentation techniques with the foreground segmented objects. The findings of this work are important in increasing the accuracies when only a small dataset is available, in creating datasets, and creating synthetic images.