EUVIMEDEUVIMED entdecken
Crossref

Noisy-Aware Unsupervised Domain Adaptation for Scene Text Recognition

Xiao-Qian Liu, Peng-Fei Zhang, Xin Luo, Zi Huang, Xin-Shun Xu

IEEE Transactions on Image Processing · 2024 · 33 · 6550-6563

DOI: 10.1109/tip.2024.3492705 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Xiao-Qian Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsupervised Domain Adaptation (UDA) has shown promise in Scene Text Recognition (STR) by facilitating knowledge transfer from labeled synthetic text (source) to more challenging unlabeled real scene text (target). However, existing UDA-based STR methods fully rely on the pseudo-labels of target samples, which ignores the impact of domain gaps (inter-domain noise) and various natural environments (intra-domain noise), resulting in poor pseudo-label quality. In this paper, we propose a novel noisy-aware unsupervised domain adaptation framework tailored for STR, which aims to enhance model robustness against both inter- and intra-domain noise, thereby providing more precise pseudo-labels for target samples. Concretely, we propose a reweighting target pseudo-labels by estimating the entropy of refined probability distributions, which mitigates the impact of domain gaps on pseudo-labels. Additionally, a decoupled triple-P-N consistency matching module is proposed, which leverages data augmentation to increase data diversity, enhancing model robustness in diverse natural environments. Within this module, we design a low-confidence-based character negative learning, which is decoupled from high-confidence-based positive learning, thus improving sample utilization under scarce target samples. Furthermore, we extend our framework to the more challenging Source-Free UDA (SFUDA) setting, where only a pre-trained source model is available for adaptation, with no access to source data. Experimental results on benchmark datasets demonstrate the effectiveness of our framework. Under the SFUDA setting, our method exhibits faster convergence and superior performance with less training data than previous UDA-based STR methods. Our method surpasses representative STR methods, establishing new state-of-the-art results across multiple datasets.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province

Zitieren

APA

Liu, X. Q., Zhang, P. F., Luo, X., Huang, Z., & Xu, X. S. (2024). Noisy-Aware Unsupervised Domain Adaptation for Scene Text Recognition. IEEE Transactions on Image Processing, 33, 6550-6563. https://doi.org/10.1109/tip.2024.3492705

Vancouver

Liu XQ, Zhang PF, Luo X, Huang Z, Xu XS. Noisy-Aware Unsupervised Domain Adaptation for Scene Text Recognition. IEEE Transactions on Image Processing. 2024;33:6550-6563. doi:10.1109/tip.2024.3492705

BibTeX
@article{Liu2024,
  author = {Liu, Xiao-Qian and Zhang, Peng-Fei and Luo, Xin and Huang, Zi and Xu, Xin-Shun},
  title = {Noisy-Aware Unsupervised Domain Adaptation for Scene Text Recognition},
  journal = {IEEE Transactions on Image Processing},
  year = {2024},
  volume = {33},
  pages = {6550--6563},
  doi = {10.1109/tip.2024.3492705}
}
Kostenlos starten →