Virtual Outliar Synthesis

1 Post

The framework of Virtual Outlier Synthesis (VOS)
Virtual Outliar Synthesis

Right-Sizing Confidence: Object Detector Lowers Confidence for Unfamiliar Inputs

An object detector trained exclusively on urban images might mistake a moose for a pedestrian and express high confidence in its poor judgment. New work enables object detectors, and potentially other neural networks, to lower their confidence when they encounter unfamiliar inputs.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox