IBM’s StarNet brings explainable AI to image classification

http://feedproxy.google.com/~r/venturebeat/SZYF/~3/h8Me1jdyStQ/

In a paper published on the preprint server Arxiv.org, researchers at IBM propose StarNet, an end-to-end trainable image classifier that’s able to localize what it believes to be the key regions supporting its predictions. Besides addressing the task of visual classification, StarNet supports the task of weakly supervised few-shot object detection,  » ….