.png){kind=icon}
Return
Sequential visual and semantic consistency for semi-supervised text recognition
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2024.01.008.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Scene text recognition (STR) is a challenging task that requires large-scale annotated data for training. However, collecting and labeling real text images is expensive and time-consuming, which limits the availability of real data. Therefore, most existing STR methods resort to synthetic data, which may introduce domain discrepancy and degrade the performance of STR models. To alleviate this problem, recent semisupervised STR methods exploit unlabeled real data by enforcing character -level consistency regularization between weakly and strongly augmented views of the same image. However, these methods neglect wordlevel consistency, which is crucial for sequence recognition tasks. This paper proposes a novel semi -supervised learning method for STR that incorporates word -level consistency regularization from both visual and semantic aspects. Specifically, we devise a shortest path alignment module to align the sequential visual features of different views and minimize their distance. Moreover, we adopt a reinforcement learning framework to optimize the semantic similarity of the predicted strings in the embedding space. We conduct extensive experiments on several standard and challenging STR benchmarks and demonstrate the superiority of our proposed method over existing semi -supervised STR methods.
Keywords:
Semi-supervised learning
Scene text recognition
Dynamic programming
Reinforcement learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.3
Papers:
8.0K
Citations:
1.6W
Organization
Cited Papers
ShareSaveHuman immunoglobulins and Fc fragments promote microtubule assembly via tau proteins and induce conformational changes of neuronal microtubules in vitro.png)
NeuroReport
NeuroReportIF0
PREAI
ShareSaveMORAN: A Multi-Object Rectified Attention Network for scene text recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave
View more