Contrastive Training for Improved Out-of-Distribution Detection
This addresses the need for reliable OOD detection in machine learning deployment, offering a practical solution without labeled OOD data, though it appears incremental as it builds on existing contrastive methods.
The paper tackles the problem of out-of-distribution (OOD) detection by proposing contrastive training, which improves performance without needing labeled OOD examples, especially in challenging 'near OOD' classes as shown on common benchmarks.
Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection performance. Unlike leading methods for OOD detection, our approach does not require access to examples labeled explicitly as OOD, which can be difficult to collect in practice. We show in extensive experiments that contrastive training significantly helps OOD detection performance on a number of common benchmarks. By introducing and employing the Confusion Log Probability (CLP) score, which quantifies the difficulty of the OOD detection task by capturing the similarity of inlier and outlier datasets, we show that our method especially improves performance in the `near OOD' classes -- a particularly challenging setting for previous methods.