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

TL;DR

FROB is a novel few-shot model that enhances classification and out-of-distribution detection robustness by combining boundary generation with self-supervised learning, effectively handling unseen OoD data and adversarial attacks.

Contribution

The paper introduces FROB, a new approach that integrates boundary generation with self-supervised learning for improved few-shot OoD detection and robustness, including zero-shot scenarios.

Findings

FROB outperforms benchmarks in robustness to outlier few-shot samples.

FROB maintains OoD detection performance regardless of few-shot size.

FROB generalizes well to unseen OoD data in real-world scenarios.

Abstract

Nowadays, classification and Out-of-Distribution (OoD) detection in the few-shot setting remain challenging aims 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 FROB 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. The 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 OoD with applicability to unknown, in the wild, test sets that do not correlate to the training datasets. To improve robustness, FROB redesigns OE to work even for zero-shots. By including our boundary, FROB reduces the threshold linked to the model's few-shot robustness; it maintains the OoD performance approximately independent of the number of few-shots. The few-shot robustness analysis evaluation of FROB on different sets and on One-Class Classification (OCC) data shows that FROB achieves competitive performance and outperforms benchmarks in terms of robustness to the outlier few-shot sample population and variability.