Bounding Box Anomaly Scoring for simple and efficient Out-of-Distribution detection
This addresses the need for reliable OOD detection to reduce unreliable predictions in deep learning, but it is incremental as it builds on existing post-hoc feature-space approaches.
The paper tackled the problem of out-of-distribution detection in deep neural networks by introducing Bounding Box Anomaly Scoring, which uses bounding-box abstraction to represent in-distribution support, resulting in robust separation between in-distribution and out-of-distribution samples on image-classification benchmarks.
Out-of-distribution (OOD) detection aims to identify inputs that differ from the training distribution in order to reduce unreliable predictions by deep neural networks. Among post-hoc feature-space approaches, OOD detection is commonly performed by approximating the in-distribution support in the representation space of a pretrained network. Existing methods often reflect a trade-off between compact parametric models, such as Mahalanobis-based scores, and more flexible but reference-based methods, such as k-nearest neighbors. Bounding-box abstraction provides an attractive intermediate perspective by representing in-distribution support through compact axis-aligned summaries of hidden activations. In this paper, we introduce Bounding Box Anomaly Scoring (BBAS), a post-hoc OOD detection method that leverages bounding-box abstraction. BBAS combines graded anomaly scores based on interval exceedances, monitoring variables adapted to convolutional layers, and decoupled clustering and box construction for richer and multi-layer representations. Experiments on image-classification benchmarks show that BBAS provides robust separation between in-distribution and out-of-distribution samples while preserving the simplicity, compactness, and updateability of the bounding-box approach.