Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models

Understand

AI Safety is a major concern in many deep learning applications such as autonomous driving.

• Given a trained deep learning model, an important natural problem is how to reliably verify the model's prediction.
• In this paper, we propose a novel framework -- deep verifier networks (DVN) to verify the inputs and outputs of deep discriminative models with deep generative models.
• Our proposed model is based on conditional variational auto-encoders with disentanglement constraints.