main.pdf (5 MB)
Download file

Towards Open-Set Text Recognition via Label-to-Prototype Learning

Download (5 MB)
posted on 2021-11-02, 01:29 authored by Chang LiuChang Liu, Chun Yang, Hai-bo Qin, Xiaobin Zhu, Xu-Cheng Yin

Scene text recognition is a popular topic and can benefit various tasks. Although many methods have been proposed for the close-set text recognition challenges, they cannot be directly applied to open-set scenarios, where the evaluation set contains novel characters not appearing in the training set. Conventional methods require collecting new data and retraining the model to handle these novel characters, which is an expensive and tedious process. In this paper, we propose a label-to-prototype learning framework to handle novel characters without retraining the model. In the proposed framework, novel characters are effectively mapped to their corresponding prototypes with a label-to-prototype learning module. This module is trained on characters with seen labels and can be easily generalized to novel characters. Additionally, feature-level rectification is conducted via topology-preserving transformation, resulting in better alignments between visual features and constructed prototypes while having a reasonably small impact on model speed. A lot of experiments show that our method achieves promising performance on a variety of zero-shot, close-set, and open-set text recognition datasets.


National Key Research and Development Program of China (2020AAA09701)

National Natural Science Foundation of China (62006018)


Email Address of Submitting Author

Submitting Author's Institution

University of Science and Technology Beijing

Submitting Author's Country


Usage metrics

Read the peer-reviewed publication

in Pattern Recognition