Semi-Supervised Text Detection With Accurate Pseudo-Labels

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 labele...

Full description

Saved in:
Bibliographic Details
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
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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).
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2022.3175667