CODiT: Conformal Out-of-Distribution Detection in Time-Series Data
It addresses safety-critical applications like autonomous vehicles and healthcare by improving OOD detection with temporal guarantees, though it builds on existing conformal methods with a novel measure.
The paper tackles out-of-distribution (OOD) detection in time-series data by proposing CODiT, which uses temporal equivariance and conformal anomaly detection to provide guarantees on false detection, achieving state-of-the-art results on autonomous driving datasets and demonstrating applicability on non-vision datasets like GAIT sensory data.
Machine learning models are prone to making incorrect predictions on inputs that are far from the training distribution. This hinders their deployment in safety-critical applications such as autonomous vehicles and healthcare. The detection of a shift from the training distribution of individual datapoints has gained attention. A number of techniques have been proposed for such out-of-distribution (OOD) detection. But in many applications, the inputs to a machine learning model form a temporal sequence. Existing techniques for OOD detection in time-series data either do not exploit temporal relationships in the sequence or do not provide any guarantees on detection. We propose using deviation from the in-distribution temporal equivariance as the non-conformity measure in conformal anomaly detection framework for OOD detection in time-series data.Computing independent predictions from multiple conformal detectors based on the proposed measure and combining these predictions by Fisher's method leads to the proposed detector CODiT with guarantees on false detection in time-series data. We illustrate the efficacy of CODiT by achieving state-of-the-art results on computer vision datasets in autonomous driving. We also show that CODiT can be used for OOD detection in non-vision datasets by performing experiments on the physiological GAIT sensory dataset. Code, data, and trained models are available at https://github.com/kaustubhsridhar/time-series-OOD.