Paper Summary: This Looks Like That: Deep Learning for Interpretable Image Recognition (NeurIPS 19)

This paper proposes a novel idea for interpretable deep learning , it basically figures out some protopyical parts of images by itself , and then uses these prototypes to make classification , hence making the classification process interpretable. Among the top 3% accepted papers of NIPS 2019.

Avatar
Aarush Gupta
Senior at IIT Roorkee

My research interests include distributed robotics, mobile computing and programmable matter.