42 citations · 204 across the 20 of their papers we have counts for
22 papers
Complementing Semi-Supervised Learning with Uncertainty Quantification
Ehsan Kazemi
The problem of fully supervised classification is that it requires a tremendous amount of annotated data, however, in many datasets a large portion of data is unlabeled. To allevia…
CTIN: Robust Contextual Transformer Network for Inertial Navigation
Bingbing Rao, Ehsan Kazemi, Yifan Ding +3
Recently, data-driven inertial navigation approaches have demonstrated their capability of using well-trained neural networks to obtain accurate position estimates from inertial me…
The Power of Subsampling in Submodular Maximization
Christopher Harshaw, Ehsan Kazemi, Moran Feldman +1
We propose subsampling as a unified algorithmic technique for submodular maximization in centralized and online settings. The idea is simple: independently sample elements from the…
Generating Structured Adversarial Attacks Using Frank-Wolfe Method
Ehsan Kazemi, Thomas Kerdreux, Liquang Wang
White box adversarial perturbations are generated via iterative optimization algorithms most often by minimizing an adversarial loss on a neighborhood of the original imag…
Trace-Norm Adversarial Examples
Ehsan Kazemi, Thomas Kerdreux, Liqiang Wang
White box adversarial perturbations are sought via iterative optimization algorithms most often minimizing an adversarial loss on a neighborhood of the original image, the so…
On Adversarial Bias and the Robustness of Fair Machine Learning
Hongyan Chang, Ta Duy Nguyen, Sasi Kumar Murakonda +2
Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behav…