5 (196) In stock
Active learning is a label-efficient machine learning method that actively selects the most valuable unlabeled samples to annotate. Active learning focuses on achieving the best possible performance while using as few, high-quality sample annotations as possible. Recently, active learning achieved promotion combined with deep learning-based methods, which are named deep active learning methods in this paper. Deep active learning plays a crucial role in computer vision tasks, especially in label-insensitive scenarios, such as hard-to-label tasks (medical images analysis) and time-consuming tasks (autonomous driving). However, deep active learning still has some challenges, such as unstable performance and dirty data, which are future research trends. Compared with other reviews on deep active learning, our work introduced the deep active learning from computer vision-related methodologies and corresponding applications. The expected audience of this vision-friendly survey are researchers who are working in computer vision but willing to utilize deep active learning methods to solve vision problems. Specifically, this review systematically focuses on the details of methods, applications, and challenges in vision tasks, and we also introduce the classic theories, strategies, and scenarios of active learning in brief.
Applied Sciences, Free Full-Text, shotgun king igg
Applied Sciences An Open Access Journal from MDPI
Applied Science
Methods and Applications of Error-Free Computation
Applied Sciences, Free Full-Text, Synthetic Dye
Applied Sciences, Free Full-Text, gas hupe dose
Applied Sciences, Free Full-Text, script king legacy mobile sem key
Applied Sciences, Free Full-Text, groups moodle ufsc
Applied Sciences, Free Full-Text, ray manchester x reader
Applied Sciences, Free Full-Text, Synthetic Dye
Applied Sciences, Free Full-Text, Emulsion
Applied Biology: An Elementary Textbook and Laboratory Guide
Science News, 41, First Edition Paperback Book, 1956
Applied Sciences, Free Full-Text, g1 f1800