CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning

by   Jingyang Lin, et al., Inc.

Localizing text instances in natural scenes is regarded as a fundamental challenge in computer vision. Nevertheless, owing to the extremely varied aspect ratios and scales of text instances in real scenes, most conventional text detectors suffer from the sub-text problem that only localizes the fragments of text instance (i.e., sub-texts). In this work, we quantitatively analyze the sub-text problem and present a simple yet effective design, COntrastive RElation (CORE) module, to mitigate that issue. CORE first leverages a vanilla relation block to model the relations among all text proposals (sub-texts of multiple text instances) and further enhances relational reasoning via instance-level sub-text discrimination in a contrastive manner. Such way naturally learns instance-aware representations of text proposals and thus facilitates scene text detection. We integrate the CORE module into a two-stage text detector of Mask R-CNN and devise our text detector CORE-Text. Extensive experiments on four benchmarks demonstrate the superiority of CORE-Text. Code is available: <>.


page 1

page 4


MOST: A Multi-Oriented Scene Text Detector with Localization Refinement

Over the past few years, the field of scene text detection has progresse...

Turning a CLIP Model into a Scene Text Spotter

We exploit the potential of the large-scale Contrastive Language-Image P...

STELA: A Real-Time Scene Text Detector with Learned Anchor

To achieve high coverage of target boxes, a normal strategy of conventio...

CentripetalText: An Efficient Text Instance Representation for Scene Text Detection

Scene text detection remains a grand challenge due to the variation in t...

ARM3D: Attention-based relation module for indoor 3D object detection

Relation context has been proved to be useful for many challenging visio...

Contextual Text Block Detection towards Scene Text Understanding

Most existing scene text detectors focus on detecting characters or word...

Detecting Multi-Oriented Text with Corner-based Region Proposals

Previous approaches for scene text detection usually rely on manually de...

Please sign up or login with your details

Forgot password? Click here to reset