Multinomial feature matching for out-of-distribution detection in synthetic aperture radar

Out-of-distribution (OOD) detection is an important part of automatic target recognition (ATR) systems. The capability to reject unknown classes improves reliability and trust in an ATR, and permits the use of otherwise closed-set classifiers where open-set recognition is necessary. In this paper we present multinomial feature matching (MFM), a method for detecting OOD data in the latent feature space of neural classifiers, and apply it to an EfficientNet-B7 model trained on the SAMPLE+ dataset. We show that MFM has efficient and low-overhead runtime characteristics, and that it exhibits a high level of performance when applied to OOD targets in SAMPLE+ and other SAR datasets, including both vehicle targets and clutter. MFM achieves a state-of-the-art area under the receiver operating characteristic (ROC) curve (AUROC) score and false positive rate (FPR) at a 95% true positive rate (TPR) (FPR@95) benchmark on the dataset, outperforming both mainstay benchmarks in OOD detection and contemporary work in the field.