Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning
Buchert F, Navab N, Kim ST (2022)
Publication Type: Conference contribution
Publication year: 2022
Journal
Publisher: Institute of Electrical and Electronics Engineers Inc.
Book Volume: 2022-August
Pages Range: 2063-2069
Conference Proceedings Title: Proceedings - International Conference on Pattern Recognition
Event location: Montreal, QC, CAN
ISBN: 9781665490627
DOI: 10.1109/ICPR56361.2022.9956305
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.
Involved external institutions
Germany (DE)
Korea, Republic of (KR)How to cite
APA:
Buchert, F., Navab, N., & Kim, S.T. (2022). Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning. In Proceedings - International Conference on Pattern Recognition (pp. 2063-2069). Montreal, QC, CAN: Institute of Electrical and Electronics Engineers Inc..
MLA:
Buchert, Felix, Nassir Navab, and Seong Tae Kim. "Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning." Proceedings of the 26th International Conference on Pattern Recognition, ICPR 2022, Montreal, QC, CAN Institute of Electrical and Electronics Engineers Inc., 2022. 2063-2069.
BibTeX: Download