Deep active learning (DeepAL) extends supervised deep learning to human-machine interactive scenarios with limited annotation budgets. Most existing DeepAL approaches for visual recognition fail to ...

A synthetic aperture radar (SAR) image classification task when the training and test sets have different distributions can be initially solved using the existing domain adaptation (DA) methods.

Technological advancements have intensified the need for a more comprehensive education across various disciplines, leading to the development of active learning methodologies to enhance the teaching ...

We introduced an algorithm for performing active learning with support vector machine and applied the algorithm to gene expression profiles of colon cancer, lung cancer, and prostate cancer samples.