Search Results for author: Roberto de M. E. Filho

Found 1 papers, 0 papers with code

Detecting Out-Of-Distribution Samples Using Low-Order Deep Features Statistics

no code implementations ICLR 2019 Igor M. Quintanilha, Roberto de M. E. Filho, José Lezama, Mauricio Delbracio, Leonardo O. Nunes

The ability to detect when an input sample was not drawn from the training distribution is an important desirable property of deep neural networks.

Benchmarking

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