A Simplified Approach to Deep Learning for Image Segmentation
This is an incremental guide aimed at practitioners needing to adapt deep learning models to specific image segmentation tasks with limited data.
The paper tackles the challenge of training deep neural networks for image segmentation on custom datasets with insufficient or homogeneous annotations, by providing a guide on data management and augmentation techniques that successfully trained two networks for pixel-wise classification.
Leaping into the rapidly developing world of deep learning is an exciting and sometimes confusing adventure. All of the advice and tutorials available can be hard to organize and work through, especially when training specific models on specific datasets, different from those originally used to train the network. In this short guide, we aim to walk the reader through the techniques that we have used to successfully train two deep neural networks for pixel-wise classification, including some data management and augmentation approaches for working with image data that may be insufficiently annotated or relatively homogenous.