ADIS-GAN: Affine Disentangled GAN

no code implementations • 1 Jan 2021 • Letao Liu, Martin Saerbeck, Justin Dauwels

This paper proposes Affine Disentangled GAN (ADIS-GAN), which is a Generative Adversarial Network that can explicitly disentangle affine transformations in a self-supervised and rigorous manner.

Generative Adversarial Network Inductive Bias +1

Affine Disentangled GAN for Interpretable and Robust AV Perception

no code implementations • 6 Jul 2019 • Letao Liu, Martin Saerbeck, Justin Dauwels

Autonomous vehicles (AV) have progressed rapidly with the advancements in computer vision algorithms.

Adversarial Attack Autonomous Vehicles +3