Tree-based data augmentation and mutual learning for offline handwritten mathematical expression recognition

Chen Yang, Jun Du, Jianshu Zhang, Changjie Wu, Mingjun Chen, Jiajia Wu

Abstract: Highlights•We propose a tree-based multi-level data augmentation strategy to effectively alleviate the problem of insufficient original annotation data, which is one of the critical technology to our champion system for the OffRaSHME20 competition.•We introduce a novel tree-based mutual learning method to deeply integrate the string decoder and the tree decoder in both the training and inference stages, which fully complement the advantages of these two types of decoders.•Our system significantly outperforms the other state-of-the-art results on both the OffRaSHME20 dataset and the CROHME14/16/19 datasets.