Semi-Supervised and Active Few-Shot Learning with Prototypical Networks
arXiv:1711.10856
Abstract
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 -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.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Wide Residual Networks
- Temporal Ensembling for Semi-Supervised Learning
- Matching Networks for One Shot Learning
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- Distributional Smoothing with Virtual Adversarial Training
- One-Shot Visual Imitation Learning via Meta-Learning
- Attentive Recurrent Comparators