GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations

5 July 2023

Papers citing "GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations"

4 / 4 papers shown

Title
On the Importance of Gradients for Detecting Distributional Shifts in the Wild Rui Huang Andrew Geng Yixuan Li 192 328 0 01 Oct 2021
Densely Connected Convolutional Networks Gao Huang Zhuang Liu L. V. D. van der Maaten Kilian Q. Weinberger PINN 3DV 255 36,362 0 25 Aug 2016
Adversarial examples in the physical world Alexey Kurakin Ian Goodfellow Samy Bengio SILM AAML 284 5,835 0 08 Jul 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,136 0 06 Jun 2015