.png){kind=icon}
.png){kind=icon}
Return
MCDAL: Maximum Classifier Discrepancy for Active Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2022.3152786.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Task analysis
Training
Learning systems
Generative adversarial networks
Semantics
Generators
Deep learning
Active learning
classifier discrepancy
data issues
deep learning
visual recognition
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W
