no code implementations • 16 Dec 2023 • Maksim Zhdanov, Stanislav Dereka, Sergey Kolesnikov
In this paper, we critically evaluate Bayesian methods for uncertainty estimation in deep learning, focusing on the widely applied Laplace approximation and its variants.
no code implementations • 19 May 2023 • Stanislav Dereka, Ivan Karpukhin, Maksim Zhdanov, Sergey Kolesnikov
Deep ensembles are capable of achieving state-of-the-art results in classification and out-of-distribution (OOD) detection.
no code implementations • 23 May 2022 • Stanislav Dereka, Ivan Karpukhin, Sergey Kolesnikov
Large-scale datasets are essential for the success of deep learning in image retrieval.
1 code implementation • 19 May 2022 • Ivan Karpukhin, Stanislav Dereka, Sergey Kolesnikov
Classification tasks are usually evaluated in terms of accuracy.
Ranked #2 on Image Classification on SVHN (Percentage correct metric)
1 code implementation • 14 Feb 2022 • Ivan Karpukhin, Stanislav Dereka, Sergey Kolesnikov
We thus provide a new confidence evaluation benchmark and establish a baseline for future confidence prediction research.