no code implementations • 3 Oct 2022 • Tiago Salvador, Kilian Fatras, Ioannis Mitliagkas, Adam Oberman
In this work, we consider the Partial Domain Adaptation (PDA) variant, where we have extra source classes not present in the target domain.
no code implementations • ICLR 2022 • Tiago Salvador, Stephanie Cairns, Vikram Voleti, Noah Marshall, Adam Oberman
However, they still have drawbacks: they reduce accuracy (AGENDA, PASS, FTC), or require retuning for different false positive rates (FSN).
no code implementations • 7 Jun 2021 • Tiago Salvador, Vikram Voleti, Alexander Iannantuono, Adam Oberman
While the primary goal is to improve accuracy under distribution shift, an important secondary goal is uncertainty estimation: evaluating the probability that the prediction of a model is correct.
no code implementations • 1 Jan 2021 • Tiago Salvador, Alexander Iannantuono, Adam M Oberman
In addition to achieving high accuracy, in many applications, it is important to estimate the probability that a model prediction is correct.
1 code implementation • 21 Mar 2019 • Adam M. Oberman, Chris Finlay, Alexander Iannantuono, Tiago Salvador
While the accuracy of modern deep learning models has significantly improved in recent years, the ability of these models to generate uncertainty estimates has not progressed to the same degree.