id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-199863-5j01k5v6	Verenich, Edward	Improving Explainability of Image Classification in Scenarios with Class Overlap: Application to COVID-19 and Pneumonia	2020-08-06		.txt	text/plain	3393	181	46	We propose a method based on binary expert networks that enhances the explainability of image classifications through better localization by mitigating the model uncertainty induced by class overlap. The standard approach in deep learning to reduce uncertainty is to provide more training data to the model, which is not always possible and primarily addresses model uncertainty Fig. 1 : The left and center images show significant overlap in the class activation maps computed by the binary classifiers for carwheels and cars, respectively. At the heart of our approach is the use of class activation maps (CAMs) for improved localization of the regions responsible for the image being in a specific class (e.g. COVID-19) as opposed to some other overlapping class (pneumonia). Our results show that training per-class binary CNN models and applying our new kernel function on their class activation maps can extract and better localize objects from overlapping classes.	./cache/cord-199863-5j01k5v6.txt	./txt/cord-199863-5j01k5v6.txt