MCDAL: Maximum Classifier Discrepancy for Active Learning

• Published in: IEEE 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
• Language: English
• 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

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...