Skip to main content

DIFFICULTY-AWARE DATA AUGMENTOR FOR SCENE TEXT RECOGNITION

Guanghao Meng (Tsinghua University); Tao Dai (Shenzhen University); Bin Chen (Harbin Institute of Technology, Shenzhen); Naiqi Li (Tsinghua-Berkeley Shenzhen Institute); Yong Jiang (Tsinghua University); Shu-Tao Xia (Tsinghua University)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
08 Jun 2023

Deep neural network (DNN) based scene text recognition (STR) methods usually require a large amount of annotated data for training, which is time-consuming and cost-expensive in practice. To address this issue, many data augmentation methods have been developed to train recognizers by improving the diversity of training samples. However, most existing methods neglect the difficulty inherent in samples, and easily suffer from the problem of \textit{over-diversity}, i.e., the distribution of the augmented data significantly deviates from that of clean data. In this paper, we propose a novel difficulty-aware data augmentation framework for scene text recognition, which jointly considers the difficulty of samples and the strength of augmentations. Specifically, our framework first predicts the sample difficulty, followed by an adaptive data augmentation strategy. Furthermore, we build a more diverse set of augmentation methods for STR and integrate it into our augmentation framework. Extensive experiments on scene text recognition benchmarks show that our augmentation framework significantly improves the performance of recognizers.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00