Graph regularization for image classification using synthesized graphs

With sincere guidance from Arjun Gopalan from the Neural Structured Learning team, we just published a tutorial on using structural similarity to regularize the training of deep neural networks for image data:

Under the hood, we represent the images of a given dataset as a synthesized graph wherein the nodes are the neighbors for a given image and the edges denote their similarity.

Works with Keras and introduces minimal technical overhead.

2 Likes