A meta-active learning approach exploiting instance importance

Sergio Flesca, Domenico Mandaglio, Francesco Scala, Andrea Tagarelli

Abstract: Highlights•A new meta-active learning strategy for deep neural network models.•The instance selection problem is modeled as a regression problem.•Four strategies of instance importance scoring by considering gradient variations.•Experiments have shown good results when few initially labeled objects are available.•A dimensionality reduction step for the instances improves the performances.