Timezone: »

 
Poster
Semantic uncertainty intervals for disentangled latent spaces
Swami Sankaranarayanan · Anastasios Angelopoulos · Stephen Bates · Yaniv Romano · Phillip Isola

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #526
in Poster Session 6 »

Meaningful uncertainty quantification in computer vision requires reasoning about semantic information---say, the hair color of the person in a photo or the location of a car on the street. To this end, recent breakthroughs in generative modeling allow us to represent semantic information in disentangled latent spaces, but providing uncertainties on the semantic latent variables has remained challenging. In this work, we provide principled uncertainty intervals that are guaranteed to contain the true semantic factors for any underlying generative model. The method does the following: (1) it uses quantile regression to output a heuristic uncertainty interval for each element in the latent space (2) calibrates these uncertainties such that they contain the true value of the latent for a new, unseen input. The endpoints of these calibrated intervals can then be propagated through the generator to produce interpretable uncertainty visualizations for each semantic factor. This technique reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in inverse problems like image super-resolution and image completion. Project page: https://swamiviv.github.io/semanticuncertaintyintervals/

Keywords: Generative Models · Uncertainty Estimation · distribution free statistics
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Swami Sankaranarayanan (Massachusetts Institute of Technology)
Anastasios Angelopoulos (UC Berkeley)
Stephen Bates (UC Berkeley)
Yaniv Romano (Technion---Israel Institute of Technology)
Phillip Isola (Massachusetts Institute of Technology)

More from the Same Authors