Detecting OODs as datapoints with High Uncertainty

Understand

Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution inputs (OODs).

• This limitation is one of the key challenges in the adoption of DNNs in high-assurance systems such as autonomous driving, air traffic management, and medical diagnosis.
• This challenge has received significant attention recently, and several techniques have been developed to detect inputs where the model's prediction cannot be trusted.
• These techniques detect OODs as datapoints with either high epistemic uncertainty or high aleatoric uncertainty.