no code implementations • 15 Jun 2023 • Moussa Kassem Sbeyti, Michelle Karg, Christian Wirth, Azarm Nowzad, Sahin Albayrak
We overcome these limitations by: (1) implementing loss attenuation in EfficientDet, and proposing two deterministic methods for the exact and fast propagation of the output distribution, (2) demonstrating on the KITTI and BDD100K datasets that the predicted uncertainty is miscalibrated, and adapting two calibration methods to the localization task, and (3) investigating the correlation between aleatoric uncertainty and task-relevant error sources.
no code implementations • ICCV 2023 • Lennart Bramlage, Michelle Karg, Cristóbal Curio
Here, we propose a straightforward human pose regression framework to examine the behavior of two established methods for simultaneous aleatoric and epistemic uncertainty estimation: maximum a-posteriori (MAP) estimation with Monte-Carlo variational inference and deep evidential regression (DER).
no code implementations • 18 Jun 2021 • Hossein Aboutalebi, Mohammad Javad Shafiee, Michelle Karg, Christian Scharfenberger, Alexander Wong
Motivated by this, this study presents the concept of residual error, a new performance measure for not only assessing the adversarial robustness of a deep neural network at the individual sample level, but also can be used to differentiate between adversarial and non-adversarial examples to facilitate for adversarial example detection.
no code implementations • 1 Aug 2020 • Hossein Aboutalebi, Mohammad Javad Shafiee, Michelle Karg, Christian Scharfenberger, Alexander Wong
In this study, we investigate the effect of adversarial machine learning on the bias and variance of a trained deep neural network and analyze how adversarial perturbations can affect the generalization of a network.
1 code implementation • CVPR 2020 • Ahmadreza Jeddi, Mohammad Javad Shafiee, Michelle Karg, Christian Scharfenberger, Alexander Wong
In this study, we introduce Learn2Perturb, an end-to-end feature perturbation learning approach for improving the adversarial robustness of deep neural networks.
no code implementations • 16 Jan 2018 • Mohammad Javad Shafiee, Brendan Chwyl, Francis Li, Rongyan Chen, Michelle Karg, Christian Scharfenberger, Alexander Wong
The computational complexity of leveraging deep neural networks for extracting deep feature representations is a significant barrier to its widespread adoption, particularly for use in embedded devices.