Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning
Authors:
- 21 August 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2063-2069
Abstract
The availability of large labeled datasets is the key component for the success of deep learning. However, annotating labels on large datasets is generally time-consuming and expensive. Active learning is a research area that addresses the issues of expensive labeling by selecting the most important samples for labeling. Diversity-based sampling algorithms are known as integral components of representation-based approaches for active learning. In this paper, we introduce a new diversity-based initial dataset selection algorithm to select the most informative set of samples for initial labeling in the active learning setting. Self-supervised representation learning is used to consider the diversity of samples in the initial dataset selection algorithm. Also, we propose a novel active learning query strategy, which uses diversity-based sampling on consistency-based embeddings. By considering the consistency information with the diversity in the consistency-based embedding scheme, the proposed method could select more informative samples for labeling in the semi-supervised learning setting. Comparative experiments show that the proposed method achieves compelling results on CIFAR-10 and Caltech-101 datasets compared with previous active learning approaches by utilizing the diversity of unlabeled data.Keywords
All Related Versions
Funding Information
- National Research Foundation
- Kyung Hee University
This publication has 8 references indexed in Scilit:
- Consistency-Based Semi-supervised Active Learning: Towards Minimizing Labeling Cost2020
- Variational Adversarial Active Learning2019
- Learning Loss for Active Learning2019
- Context Encoders: Feature Learning by Inpainting2016
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Multi-class active learning for image classification2009
- Margin-Based Active Learning for Structured Output Spaces2006
- Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories2005