Maskstr: Guide Scene Text Recognition Models with Masking
Lists
Only you see this
Abstract
Text recognition in information loss scenarios like blurriness, occlusion, and perspective distortion is challenging in real-world applications. To enhance robustness, some studies use extra unlabeled data for encoder pretraining. Others focus on improving decoder context reasoning. However, pretraining methods require abundant unlabeled data and high computing resources, while decoder-based approaches risk over-correction. In this paper, we propose MaskSTR, a dual-branch training framework for STR models, using patch masking to simulate information loss. MaskSTR guides visual representation learning, improving robustness to information loss conditions without extra data or training stages. Furthermore, we introduce Block Masking, a novel and straightforward mask generation method, for further performance enhancement. Experiments demonstrate MaskSTR’s effectiveness across CTC, attention, and Transformer decoding methods, achieving significant performance gains and setting new state-of-the-art results.
BibTeX
@inproceedings{wei2024maskstr,
author = {Baole Wei and Minghang He and Liangcai Gao and Duoyou Zhou and Xiang Bai and Zhi Tang},
title = {{Maskstr: Guide Scene Text Recognition Models with Masking}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2024},
doi = {10.1109/icassp48485.2024.10446874},
}Loading related content...