Improved Few-Shot Visual Classification

Few-shot learning is a fiindamental task in computer vision that carries the promise of alleviating the need for exhaustively labeled data. Most few-shot learning approaches to date have Pulsed on progressively more complex neural feature extractors and classifier adaptation strategies, and the refinement of the task definition itself: In this paper, we explore the hypothesis that a simple class-covariance-based distance metric, namely the Mahalanobis distance, adopted into a state of the art few-shot learning approach (CNAPS [30]) can, in and of itself lead to a significant performance improvement. We also discover that it is possible to learn adaptive feature extractors that allow usefid estimation of the high dimensional feature covariances required by this metric from surprisingly few samples. The result of our work is a new "Simple CNAPS" architecture which has up to 9.2% fewer trainable parameters than CNAPS and performs up to 6.1% better than state of the art on the standard few-shot image classification benchmark dataset.