Task Cooperation for Semi-Supervised Few-Shot Learning

Authors

  • Han-Jia Ye State Key Laboratory for Novel Software Technology, Nanjing University
  • Xin-Chun Li State Key Laboratory for Novel Software Technology, Nanjing University
  • De-Chuan Zhan State Key Laboratory for Novel Software Technology, Nanjing University

Keywords:

Transfer/Adaptation/Multi-task/Meta/Automated Learning, Semi-Supervised Learning, Representation Learning

Abstract

Training a model with limited data is an essential task for machine learning and visual recognition. Few-shot learning approaches meta-learn a task-level inductive bias from SEEN class few-shot tasks, and the meta-model is expected to facilitate the few-shot learning with UNSEEN classes. Inspired by the idea that unlabeled data can be utilized to smooth the model space in traditional semi-supervised learning, we propose TAsk COoperation (TACO) which takes advantage of unsupervised tasks to smooth the meta-model space. Specifically, we couple the labeled support set in a few-shot task with easily-collected unlabeled instances, prediction agreement on which encodes the relationship between tasks. The learned smooth meta-model promotes the generalization ability on supervised UNSEEN few-shot tasks. The state-of-the-art few-shot classification results on MiniImageNet and TieredImageNet verify the superiority of TACO to leverage unlabeled data and task relationship in meta-learning.

Downloads

Published

2021-05-18

How to Cite

Ye, H.-J., Li, X.-C., & Zhan, D.-C. (2021). Task Cooperation for Semi-Supervised Few-Shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(12), 10682-10690. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17277

Issue

Section

AAAI Technical Track on Machine Learning V