Out-of-Distribution Detection Based on Total Variation Estimation
This addresses the problem of model robustness for practical deployments, but appears incremental as it builds on existing out-of-distribution detection methods.
The paper tackles the problem of detecting out-of-distribution data to secure machine learning models against distribution shifts, introducing the TV-OOD method that uses total variation estimation to calculate scores for discrimination, achieving results comparable or superior to leading-edge techniques across all evaluation metrics in image classification tasks.
This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Distribution (TV-OOD) detection method. Existing methods have produced satisfactory results, but TV-OOD improves upon these by leveraging the Total Variation Network Estimator to calculate each input's contribution to the overall total variation. By defining this as the total variation score, TV-OOD discriminates between in- and out-of-distribution data. The method's efficacy was tested across a range of models and datasets, consistently yielding results in image classification tasks that were either comparable or superior to those achieved by leading-edge out-of-distribution detection techniques across all evaluation metrics.