1 code implementation • 5 Mar 2024 • Dharmesh Tailor, Aditya Patra, Rajeev Verma, Putra Manggala, Eric Nalisnick
The learning to defer (L2D) framework allows autonomous systems to be safe and robust by allocating difficult decisions to a human expert.
1 code implementation • 30 Oct 2022 • Rajeev Verma, Daniel Barrejón, Eric Nalisnick
We study the statistical properties of learning to defer (L2D) to multiple experts.
1 code implementation • 8 Feb 2022 • Rajeev Verma, Eric Nalisnick
We find that Mozannar & Sontag's (2020) multiclass framework is not calibrated with respect to expert correctness.
1 code implementation • RC 2020 • Rajeev Verma, Jim Wagemans, Paras Dahal, Auke Elfrink
We reproduce the original experiments using their source code.
1 code implementation • ACL 2019 • Tirthankar Ghosal, Rajeev Verma, Asif Ekbal, Pushpak Bhattacharyya
However, the peer review texts, which contains rich sentiment information of the reviewer, reflecting his/her overall attitude towards the research in the paper, could be a valuable entity to predict the acceptance or rejection of the manuscript under consideration.
no code implementations • 5 Apr 2019 • Richard McKinley, Lorenz Grunder, Rik Wepfer, Fabian Aschwanden, Tim Fischer, Christoph Friedli, Raphaela Muri, Christian Rummel, Rajeev Verma, Christian Weisstanner, Mauricio Reyes, Anke Salmen, Andrew Chan, Roland Wiest, Franca Wagner
Instead, we propose a method for identifying lesion changes of high certainty, and establish on a dataset of longitudinal multiple sclerosis cases that this method is able to separate progressive from stable timepoints with a very high level of discrimination (AUC = 0. 99), while changes in lesion volume are much less able to perform this separation (AUC = 0. 71).
no code implementations • 22 Jan 2019 • Richard McKinley, Rik Wepfer, Fabian Aschwanden, Lorenz Grunder, Raphaela Muri, Christian Rummel, Rajeev Verma, Christian Weisstanner, Mauricio Reyes, Anke Salmen, Andrew Chan, Franca Wagner, Roland Wiest
We trained two state-of-the-art fully convolutional CNN architectures on the 2016 MSSEG training dataset, which was annotated by seven independent human raters: a reference implementation of a 3D Unet, and a more recently proposed 3D-to-2D architecture (DeepSCAN).