Bridging In- and Out-of-distribution Samples for Their Better Discriminability

Understand

This paper proposes a method for OOD detection.

• Questioning the premise of previous studies that ID and OOD samples are separated distinctly, we consider samples lying in the intermediate of the two and use them for training a network.
• We generate such samples using multiple image transformations that corrupt inputs in various ways and with different severity levels.
• We estimate where the generated samples by a single image transformation lie between ID and OOD using a network trained on clean ID samples.