MCDAL: Maximum Classifier Discrepancy for Active Learning

Recent state-of-the-art active learning methods have mostly leveraged generative adversarial networks (GANs) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyperparameters. In contrast to these methods, in this article, we propose a novel active l...

Full description

Saved in:
Bibliographic Details
Published inIEEE transaction on neural networks and learning systems Vol. 34; no. 11; pp. 8753 - 8763
Main Authors Cho, Jae Won, Kim, Dong-Jin, Jung, Yunjae, Kweon, In So
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.11.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Active learning
Classification
classifier discrepancy
Classifiers
data issues
Deep learning
Generative adversarial networks
Generators
Image classification
Image processing
Image segmentation
Learning
Learning systems
Predictions
Semantic segmentation
Semantics
Task analysis
Teaching methods
Training
visual recognition
Online AccessGet full text

Cover

More Information
Summary:Recent state-of-the-art active learning methods have mostly leveraged generative adversarial networks (GANs) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyperparameters. In contrast to these methods, in this article, we propose a novel active learning framework that we call Maximum Classifier Discrepancy for Active Learning (MCDAL) that takes the prediction discrepancies between multiple classifiers. In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them. Intuitively, the discrepancies in the auxiliary classification layers' predictions indicate the uncertainty in the prediction. In this regard, we propose a novel method to leverage the classifier discrepancies for the acquisition function for active learning. We also provide an interpretation of our idea in relation to existing GAN-based active learning methods and domain adaptation frameworks. Moreover, we empirically demonstrate the utility of our approach where the performance of our approach exceeds the state-of-the-art methods on several image classification and semantic segmentation datasets in active learning setups.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2022.3152786