Search Results for author: Brian Potetz

Found 2 papers, 1 papers with code

Geo-Aware Networks for Fine-Grained Recognition

1 code implementation4 Jun 2019 Grace Chu, Brian Potetz, Weijun Wang, Andrew Howard, Yang song, Fernando Brucher, Thomas Leung, Hartwig Adam

By leveraging geolocation information we improve top-1 accuracy in iNaturalist from 70. 1% to 79. 0% for a strong baseline image-only model.

Fine-Grained Image Classification General Classification

Whitened Expectation Propagation: Non-Lambertian Shape from Shading and Shadow

no code implementations CVPR 2013 Brian Potetz, Mohammadreza Hajiarbabi

Difficulties in performing optimization efficiently have limited the probabilistic models explored in computer vision and other fields.

Cannot find the paper you are looking for? You can Submit a new open access paper.