- TL;DR: We develop an approach for the novel and challenging few-shot one-class classification problem and validate it on datasets from the image and time-series domain, including a real-world dataset of industrial sensor readings.
- Abstract: Although few-shot learning and one-class classification have been separately well studied, their intersection remains rather unexplored. Our work addresses the few-shot one-class classification problem and presents a meta-learning approach that requires only few data examples from only one class to adapt to unseen tasks. The proposed method builds upon the model-agnostic meta-learning (MAML) algorithm (Finn et al., 2017) and explicitly trains for few-shot class-imbalance learning, aiming to learn a model initialization that is particularly suited for learning one-class classification tasks after observing only a few examples of one class. Experimental results on datasets from the image domain and the time-series domain show that our model substantially outperforms the baselines, including MAML, and demonstrate the ability to learn new tasks from only few majority class samples. Moreover, we successfully learn anomaly detectors for a real world application involving sensor readings recorded during industrial manufacturing of workpieces with a CNC milling machine using only few examples from the normal class.
- Keywords: meta-learning, few-shot learning, one-class classification, class-imbalance learning