Gifsplanation via Latent Shift

The goal of a prediction explanation method is to identify features which are relevant to the prediction of a neural network and convey that information to the user.

The method shown above is called Latent Shift. This method looks at what pixels change when the image is simulated to have more or less of the specific pathology. Each frame of this video is simulated. The video starts with the pathology removed and proceeds to add the pathology before reversing and starting the loop over again.

Demo webpage: https://mlmed.org/gifsplanation

Source code: https://github.com/mlmed/gifsplanation

Paper: https://arxiv.org/abs/2102.09475