VPDL: Visual Prompt-Guided Differential Learning for Generalizable Scene Text Recognition
Journal of Advanced Computational Intelligence and Intelligent Informatics · 20.07.2026 · 30 (4) · 1306-1317
DOI: 10.20965/jaciii.2026.p1306 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advanced Computational Intelligence and Intelligent Informatics, online erschienen am 20.07.2026. Verfasst von Yali Niu und 2 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben.
Abstract (Originalsprache)
Scene text recognition (STR) in natural images remains highly challenging due to the large variations in character appearance across diverse real-world conditions, such as changes in font, color, layout, and background complexity—which hinder model generalization and remain insufficiently explored. To address this issue, we propose a visual prompt-guided differential learning (VPDL) framework designed to improve the generalization capability of STR models without requiring scene-specific fine-tuning. Inspired by the human ability to reference prior visual knowledge when recognizing text, VPDL introduces a set of character-level visual prompts that guide the model in perceiving appearance variations among characters. Built upon these prompts, we develop a local-to-global differential learning strategy that enhances patch-level representations and aligns global features with character cues while preserving scene-specific information. Additionally, to mitigate exposure bias in autoregressive decoding, we replace conventional label inputs with context-aware textual prompts, encouraging the decoder to better utilize textual cues embedded in image features. Extensive experiments on widely used benchmarks and real-world datasets demonstrate the effectiveness of VPDL.
Zitieren
APA
Niu, Y., An, J., & Zou, S. (2026). VPDL: Visual Prompt-Guided Differential Learning for Generalizable Scene Text Recognition. Journal of Advanced Computational Intelligence and Intelligent Informatics, 30(4), 1306-1317. https://doi.org/10.20965/jaciii.2026.p1306
Vancouver
Niu Y, An J, Zou S. VPDL: Visual Prompt-Guided Differential Learning for Generalizable Scene Text Recognition. Journal of Advanced Computational Intelligence and Intelligent Informatics. 2026;30(4):1306-1317. doi:10.20965/jaciii.2026.p1306
BibTeX
@article{Niu2026,
author = {Niu, Yali and An, Jiahao and Zou, Shihao},
title = {VPDL: Visual Prompt-Guided Differential Learning for Generalizable Scene Text Recognition},
journal = {Journal of Advanced Computational Intelligence and Intelligent Informatics},
year = {2026},
volume = {30},
number = {4},
pages = {1306--1317},
doi = {10.20965/jaciii.2026.p1306}
}
EUVIMED