Oracle Character Recognition using Unsupervised Discriminative Consistency Network
This work addresses the challenge of recognizing ancient oracle characters, which is important for historical studies, by providing an incremental improvement in a domain-specific application.
The paper tackles oracle character recognition by proposing an unsupervised domain adaptation method to transfer knowledge from labeled handprinted characters to unlabeled scanned data, achieving state-of-the-art results with a 15.1% improvement over a recent baseline on the Oracle-241 dataset.
Ancient history relies on the study of ancient characters. However, real-world scanned oracle characters are difficult to collect and annotate, posing a major obstacle for oracle character recognition (OrCR). Besides, serious abrasion and inter-class similarity also make OrCR more challenging. In this paper, we propose a novel unsupervised domain adaptation method for OrCR, which enables to transfer knowledge from labeled handprinted oracle characters to unlabeled scanned data. We leverage pseudo-labeling to incorporate the semantic information into adaptation and constrain augmentation consistency to make the predictions of scanned samples consistent under different perturbations, leading to the model robustness to abrasion, stain and distortion. Simultaneously, an unsupervised transition loss is proposed to learn more discriminative features on the scanned domain by optimizing both between-class and within-class transition probability. Extensive experiments show that our approach achieves state-of-the-art result on Oracle-241 dataset and substantially outperforms the recently proposed structure-texture separation network by 15.1%.