In many applications, we are constrained to learn classifiers from very limited data (few-shot classification). The task becomes even more challenging if it is also required to identify samples from unknown categories (open-set classification). Learning a good abstraction for a class with very few samples is extremely difficult, especially under open-set settings. As a result, open-set recognition has received minimal attention in the few-shot setting. However, it is a critical task in many applications like environmental monitoring, where the number of labeled examples for each class is limited. Existing few-shot open-set recognition (FSOSR) methods rely on thresholding schemes, with some considering uniform probability for open-class samples. However, this approach is often inaccurate, especially for fine-grained categorization, and makes them highly sensitive to the choice of a threshold. To address these concerns, we propose Reconstructing Exemplar-based Few-shot Open-set ClaSsifier (ReFOCS). By using a novel exemplar reconstruction-based meta-learning strategy ReFOCS streamlines FSOSR eliminating the need for a carefully tuned threshold by learning to be self-aware of the openness of a sample. The exemplars, act as class representatives and can be either provided in the training dataset or estimated in the feature domain. By testing on a wide variety of datasets, we show ReFOCS to outperform multiple state-of-the-art methods.

翻译：在许多实际应用中，我们受限于从极少量数据中学习分类器（即少样本分类）。若还需识别未知类别的样本（即开放集分类），该任务将更具挑战性。在开放集场景下，针对仅有极少样本的类别学习良好的抽象表征极为困难。因此，开放集识别在少样本领域鲜受关注。然而，在环境监测等应用中，每个类别的标注样本数量有限，该任务十分关键。现有少样本开放集识别（FSOSR）方法依赖于阈值设定方案，部分方法假设开放类样本具有均匀概率分布。但这种策略通常不准确（尤其在细粒度分类中），且高度依赖阈值的选取。为解决这些问题，我们提出基于样本重建的少样本开放集分类器（ReFOCS）。通过一种新颖的基于样本重建的元学习策略，ReFOCS简化了FSOSR流程，使模型通过学习感知样本的开放性，从而无需精细调节阈值。样本原型作为类的代表，既可由训练数据集提供，也可在特征域中估计。在多种数据集上的实验表明，ReFOCS优于多种最新方法。