Active One-shot Learning

Abstract

Recent advances in one-shot learning have produced models that can learn from a handful of labeled examples, for passive classification and regression tasks. This paper combines reinforcement learning with one-shot learning, allowing the model to decide, during classification, which examples are worth labeling. We introduce a classification task in which a stream of images are presented and, on each time step, a decision must be made to either predict a label or pay to receive the correct label. We present a recurrent neural network based action-value function, and demonstrate its ability to learn how and when to request labels. Through the choice of reward function, the model can achieve a higher prediction accuracy than a similar model on a purely supervised task, or trade prediction accuracy for fewer label requests.

NIPS 2016, Deep Reinforcement Learning Workshop, Barcelona, Spain. See https://cs.stanford.edu/~woodward/ for the poster and a short video description of the paper

Cited by in corpus (15)

• Learning Algorithms for Active Learning
• Active Learning: Problem Settings and Recent Developments
• Reinforced active learning for image segmentation
• A Meta-Learning Approach to One-Step Active Learning
• Generative One-Shot Learning (GOL): A Semi-Parametric Approach to One-Shot Learning in Autonomous Vision
• Meta-Learning for Contextual Bandit Exploration
• Learning to Sample the Most Useful Training Patches from Images
• MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning
• Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification
• Meta-Learning via Feature-Label Memory Network
• Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms
• Variable-Shot Adaptation for Online Meta-Learning
• A Review of Computer Vision Methods in Network Security
• MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning
• ImitAL: Learning Active Learning Strategies from Synthetic Data