Nearest Neighbor Classifier Embedded Network for Active Learning

Authors

  • Fang Wan University of Chinese Academy of Sciences
  • Tianning Yuan University of Chinese Academy of Sciences
  • Mengying Fu University of Chinese Academy of Sciences
  • Xiangyang Ji Tsinghua University
  • Qingming Huang University of Chinese Academy of Sciences
  • Qixiang Ye University of Chinese Academy of Sciences, China

Keywords:

Active Learning

Abstract

Deep neural networks (DNNs) have been widely applied to active learning. Despite of its effectiveness, the generalization ability of the discriminative classifier (the softmax classifier) is questionable when there is a significant distribution bias between the labeled set and the unlabeled set. In this paper, we attempt to replace the softmax classifier in deep neural network with a nearest neighbor classifier, considering its progressive generalization ability within the unknown sub-space. Our proposed active learning approach, termed nearest Neighbor Classifier Embedded network (NCE-Net), targets at reducing the risk of over-estimating unlabeled samples while improving the opportunity to query informative samples. NCE-Net is conceptually simple but surprisingly powerful, as justified from the perspective of the subset information, which defines a metric to quantify model generalization ability in active learning. Experimental results show that, with simple selection based on rejection or confusion confidence, NCE-Net improves state-of-the-arts on image classification and object detection tasks with significant margins.

Downloads

Published

2021-05-18

How to Cite

Wan, F., Yuan, T., Fu, M., Ji, X., Huang, Q., & Ye, Q. (2021). Nearest Neighbor Classifier Embedded Network for Active Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 10041-10048. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17205

Issue

Section

AAAI Technical Track on Machine Learning IV