Semi-Supervised and Active Few-Shot Learning with Prototypical Networks
This addresses few-shot learning for scenarios with limited labeled data, but it is incremental as it builds on existing Prototypical Networks.
The paper tackles semi-supervised few-shot classification by using Prototypical Networks with K-means clustering guided by labeled examples, and shows that active adaptation via user feedback improves performance on image data.
We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled examples. We propose a clustering approach to the problem. The features extracted with Prototypical Networks are clustered using $K$-means with the few labeled examples guiding the clustering process. We note that in many real-world applications the adaptation performance can be significantly improved by requesting the few labels through user feedback. We demonstrate good performance of the active adaptation strategy using image data.