no code implementations • 6 Apr 2023 • Jinsol Lee, Charlie Lehman, Mohit Prabhushankar, Ghassan AlRegib
We define purview as the additional capacity necessary to characterize inference samples that differ from the training data.
no code implementations • 16 Jun 2022 • Jinsol Lee, Mohit Prabhushankar, Ghassan AlRegib
We propose to utilize gradients for detecting adversarial and out-of-distribution samples.
no code implementations • 16 Jun 2022 • Jinsol Lee, Ghassan AlRegib
Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes.
no code implementations • 18 Aug 2020 • Jinsol Lee, Ghassan AlRegib
We demonstrate the effectiveness of gradients as a measure of model uncertainty in applications of detecting unfamiliar inputs, including out-of-distribution and corrupted samples.
1 code implementation • 18 Feb 2019 • Dogancan Temel, Jinsol Lee, Ghassan AlRegib
Experimental results show that deep learning-based image representations can estimate the recognition performance variation with a Spearman's rank-order correlation of 0. 94 under multifarious acquisition conditions.
1 code implementation • 18 Oct 2018 • Dogancan Temel, Jinsol Lee, Ghassan AlRegib
Moreover, we investigate the relationship between object recognition and image quality and show that objective quality algorithms can estimate recognition performance under certain photometric challenging conditions.