Semi-Supervised Text Detection With Accurate Pseudo-Labels

• Published in: IEEE signal processing letters 2022, Vol.29, p.1272-1276
• Main Authors: Zhou, Yu, Xie, Hongtao, Fang, Shancheng, Zhang, Yongdong
• Format: Article
• Language: English
• Subjects: Adaptation models; Algorithms; Data models; Deep learning; Detection algorithms; Feature extraction; Labels; loss function; multi-scale text; Prediction algorithms; semi-supervised text detection; Signal processing algorithms; Texts; Training
• ISSN: 1070-9908; 1558-2361
• DOI: 10.1109/LSP.2022.3175667

Recent scene text detection methods have made great progress. However, existing methods rely heavily on extensive labeled data, which is very time-consuming and expensive. In this letter, we propose a novel semi-supervised text detection method to alleviate the dependence of text detectors on labeled data by generating accurate pseudo-labels and performing effective data augmentations. Specifically, a dual-threshold pseudo-label generation algorithm is designed to divide the prediction results into background regions, text regions, and uncertain regions. The definition of uncertain regions obviously improves the accuracy of pseudo-labels. To obtain accurate pseudo-labels for text at various scales, we first design a scale-aware loss function to adaptively adjust the loss weight of different scale texts. Then, a multi-scale feature extraction module is proposed to extract multi-scale text features and adaptively weight these features according to the scale of the text. Moreover, effective data augmentations are explored to use unlabeled data to improve the robustness of the model to various texts. Experiments show that our method achieves state-of-the-art performance on several datasets(e.g., outperforms existing methods by 2.0% on TD500).