Journal Article

A Text-Specific Domain Adaptive Network for Scene Text Detection in the Wild

He, Xuan, Li, Mengyao, Yuan, Jin, Wang, Haidong, Wang, Runmin, Li, Zhiyong

2023

Overview

Scene text detection has drawn increasing attention due to its potential scalability to large-scale applications. Currently, a well-trained scene text detection model on a source domain usually has unsatisfactory performance when it is migrated to e large domain shift between them. To bridge this gap, this paper proposes a novel network integrates both text-specific Faster R-CNN (ts-FRCNN) and domain adaptation (ts-DA) into one framework. Compared to conventional FRCNN, ts-FRCNN designs a text-specific RPN to generate more accurate region proposals by considering the inherent characters of scene text, as well as text-specific RoI pooling to extract purer and sufficient fine-grained text features by adopting an adaptive asymmetric griding strategy. Compared to conventional domain adaptation, ts-DA adopts a triple-level alignment strategy to reduce the domain shift at the image, word and character levels, and builds a triple-consistency regularization among them, which significantly promotes domain-invariant text feature learning. We conduct extensive experiments on three representative transfer learning tasks: common-to-extreme scenes, real-to-real scenes and synthetic-to-real scenes. The experimental results demonstrate that our model consistently outperforms the previous methods.

• Publisher: Springer Nature B.V
• Subject: Adaptation / Cognitive tasks / Regularization