1 code implementation • 18 Feb 2023 • Nihal Murali, Aahlad Puli, Ke Yu, Rajesh Ranganath, Kayhan Batmanghelich
(3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN's early layers.
no code implementations • 21 Oct 2022 • Sumedha Singla, Nihal Murali, Forough Arabshahi, Sofia Triantafyllou, Kayhan Batmanghelich
The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples that lie close to the decision boundary.