FROB: Few-shot ROBust Model for Classification with Out-of-Distribution Detection

Nowadays, classification and Out-of-Distribution (OoD) detection in the few-shot setting remain challenging aims mainly due to rarity and the limited samples in the few-shot setting, and because of adversarial attacks. Accomplishing these aims is important for critical systems in safety, security, and defence. In parallel, OoD detection is challenging since deep neural network classifiers set high confidence to OoD samples away from the training data. To address such limitations, we propose the Few-shot ROBust (FROB) model for classification and few-shot OoD detection. We devise a methodology for improved robustness and reliable confidence prediction for few-shot OoD detection. We generate the support boundary of the normal class distribution and combine it with few-shot Outlier Exposure (OE). We propose a self-supervised learning few-shot confidence boundary methodology based on generative and discriminative models, including classification. The main contribution of FROB is the combination of the generated boundary in a self-supervised learning manner and the imposition of low confidence at this learned boundary. FROB implicitly generates strong adversarial samples on the boundary and forces samples from OoD, including our boundary, to be less confident by the classifier. FROB achieves generalization to unseen anomalies and adversarial attacks, with applicability to unknown, in the wild, test sets that do not correlate to the training datasets. To improve robustness, FROB redesigns and streamlines OE to work even for zero-shots. By including our learned boundary, FROB effectively reduces the threshold linked to the model’s few-shot robustness, and maintains the OoD performance approximately constant and independent of the number of few-shot samples. The few-shot robustness analysis evaluation of FROB on different image sets and on One-Class Classification (OCC) data shows that FROB achieves competitive state-of-the-art performance and outperforms benchmarks in terms of robustness to the outlier OoD few-shot sample population and variability.