Local Background Estimation for Improved Gas Plume Identification in Hyperspectral Images

no code implementations • 23 Jan 2024 • Scout Jarman, Zigfried Hampel-Arias, Adra Carr, Kevin R. Moon

Deep learning identification models have shown promise for identifying gas plumes in Longwave IR hyperspectral images of urban scenes, particularly when a large library of gases are being considered.

Image Segmentation Semantic Segmentation

A general approach to bridge the reality-gap

no code implementations • 3 Sep 2020 • Michael Lomnitz, Zigfried Hampel-Arias, Nina Lopatina, Felipe A. Mejia

Employing machine learning models in the real world requires collecting large amounts of data, which is both time consuming and costly to collect.

BIG-bench Machine Learning Data Augmentation +2

Reducing audio membership inference attack accuracy to chance: 4 defenses

no code implementations • 31 Oct 2019 • Michael Lomnitz, Nina Lopatina, Paul Gamble, Zigfried Hampel-Arias, Lucas Tindall, Felipe A. Mejia, Maria Alejandra Barrios

It is critical to understand the privacy and robustness vulnerabilities of machine learning models, as their implementation expands in scope.

Inference Attack Membership Inference Attack +1

Robust or Private? Adversarial Training Makes Models More Vulnerable to Privacy Attacks

no code implementations • 15 Jun 2019 • Felipe A. Mejia, Paul Gamble, Zigfried Hampel-Arias, Michael Lomnitz, Nina Lopatina, Lucas Tindall, Maria Alejandra Barrios

Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks.

Generative Adversarial Network