Labeling of datasets is an essential task for supervised and semi-supervised machine learning. Model-based active learning and user-based interactive labeling are two complementary strategies for this task.
We propose VisGIL which, using visual cues, guides the user in the selection of instances to label based on utility measures deduced from an active learning model.
Combining Active Learning and user guidance
Journal paper (substantially extended from conference paper below): VisGIL: Machine Learning based Visual Guidance for Interactive Labeling Grimmeisen, B. and Chegini, M. and Theissler, A. (2021).(under review)
Conference paper: The Machine Learning Model as a Guide: Pointing Users to Interesting Instances for Labeling through Visual Cues. Grimmeisen, B. and Theissler, A. (2020). 13th International Symposium on Visual Information Communication and Interaction (VINCI 2020). ACM, ISBN: 978-1-4503-8750-7. Download , Link to paper