Chapter 4: Using t-SNE Plots as a Human-AI Translator

History: For my masters research project at University of Toronto, I was given airport Xray baggage scan images containing gun and knife to develop a model that performs an automatic detection of gun and knife in the baggage. Given only a small amount of Xray images, I am using Domain Adaptation by using a large number of normal non-Xray images of gun and knife from the web to train a model and adapting the model to perform well on the Xray images. In this post, I will address a strange behaviour of ResNet50 and show how the t-SNE visualization technique helped clear up the fog. In Chapter 3.2, I addressed a concerning and unintuitive behaviour of ResNet50 that was fine-tuned for gun vs. knife binary classification task using only web images (no Xray images). It classified images unrelated to gun or knife (e.g.