Active Learning and Transfer Learning for Document Segmentation
Dmitry Maratovich Kiranov, Maxim Alexeevitch Ryndin, Ilya Sergeevich Kozlov · Programming and Computer Software · 2023
Abstract In this paper, we investigate the effectiveness of classical approaches to active learning in the problem of document segmentation with the aim of reducing the size of the training sample. A modified approach to selection of document images for labeling and subsequent model training is presented. The results of active learning are compared to those of transfer learning on fully labeled data. The paper also investigates how the problem domain of a training set, on which a model is initialized for transfer learning, affects the subsequent uptraining of the model.