Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation

Understand

Calibrated estimates of uncertainty are critical for many real-world computer vision applications of deep learning.

• While there are several widely-used uncertainty estimation methods, dropout inference stands out for its simplicity and efficacy.
• This technique, however, requires multiple forward passes through the network during inference and therefore can be too resource-intensive to be deployed in real-time applications.
• We propose a simple, easy-to-optimize distillation method for learning the conditional predictive distribution of a pre-trained dropout model for fast, sample-free uncertainty estimation in computer vision tasks.