iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
This addresses the need for reliable OOD detection to prevent incorrect predictions in safety-critical domains, representing a strong specific gain.
The paper tackles the problem of out-of-distribution (OOD) detection for deep neural networks in safety-critical applications by proposing iDECODe, a method that uses in-distribution equivariance and conformal prediction to guarantee a bounded false detection rate, achieving state-of-the-art results on image and audio datasets.
Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confidence on inputs outside their training distribution. The deployment of DNNs in safety-critical domains requires detection of out-of-distribution (OOD) data so that DNNs can abstain from making predictions on those. A number of methods have been recently developed for OOD detection, but there is still room for improvement. We propose the new method iDECODe, leveraging in-distribution equivariance for conformal OOD detection. It relies on a novel base non-conformity measure and a new aggregation method, used in the inductive conformal anomaly detection framework, thereby guaranteeing a bounded false detection rate. We demonstrate the efficacy of iDECODe by experiments on image and audio datasets, obtaining state-of-the-art results. We also show that iDECODe can detect adversarial examples.