.png){kind=icon}
返回
Masked and Permuted Implicit Context Learning for Scene Text Recognition
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2024.3381893.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Scene Text Recognition (STR) is challenging because of various text styles, shapes, and backgrounds. Although the integration of linguistic information enhances models' performance, existing methods based on either permuted language modeling (PLM) or masked language modeling (MLM) have their drawbacks. PLM's autoregressive decoding lacks foresight into subsequent characters, while MLM overlooks inter-character dependencies. To address these problems, we propose a masked and permuted implicit context learning network for STR, which unifies PLM and MLM within a single decoder, inheriting the advantages of both approaches. We utilize the training procedure of PLM and incorporate word length information into the decoding process to integrate MLM, substituting the undetermined characters with mask tokens. Besides, we employ the perturbation training technique to train a more robust model against potential length prediction errors. Our comprehensive evaluations demonstrate the performance of our model. It achieves superior performance on the popularly used benchmarks and outperforms previous state-of-the-art methods with a substantial improvement of 9.1% on the more challenging Union14M-Benchmark.
Keyword:
Decoding
Training
Context modeling
Predictive models
Iterative decoding
Visualization
Benchmark testing
Autoregressive
language modeling
non-autoregressive
OCR
scene text recognition
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
The tunability and dielectric properties of the compositionally graded Ba(Zr x Ti1−x )O3 thin films
PREAI
分享收藏
Human immunoglobulins and Fc fragments promote microtubule assembly via tau proteins and induce conformational changes of neuronal microtubules in vitro.png)
NeuroReport
NeuroReportIF0
PREAI
分享收藏
查看更多内容