Generative Visual Rationales

no code implementations • 4 Apr 2018 • Jarrel Seah, Jennifer Tang, Andy Kitchen, Jonathan Seah

For each prediction, we generate visual rationales by optimizing a latent representation to minimize the prediction of disease while constrained by a similarity measure in image space.

Thinking like a machine — generating visual rationales through latent space optimization

no code implementations • ICLR 2018 • Jarrel Seah, Jennifer Tang, Andy Kitchen, Jonathan Seah

For each prediction, we generate visual rationales for positive classifications by optimizing a latent representation to minimize the probability of disease while constrained by a similarity measure in image space.