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

arXiv: https://arxiv.org/abs/2112.07513 · HTML: https://mlsanity.com/paper/2112.07513/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 14 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [Exploring Visual Relationship for Image Captioning](https://mlsanity.com/paper/1809.07041/) (2018)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [X-Linear Attention Networks for Image Captioning](https://mlsanity.com/paper/2003.14080/) (2020)
- [Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition](https://mlsanity.com/paper/1710.10400/) (2017)
- [Shape Robust Text Detection with Progressive Scale Expansion Network](https://mlsanity.com/paper/1903.12473/) (2019)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Detecting Text in Natural Image with Connectionist Text Proposal Network](https://mlsanity.com/paper/1609.03605/) (2016)
- [Detecting Curve Text in the Wild: New Dataset and New Solution](https://mlsanity.com/paper/1712.02170/) (2017)
- [Detecting Oriented Text in Natural Images by Linking Segments](https://mlsanity.com/paper/1703.06520/) (2017)
- [Relation Distillation Networks for Video Object Detection](https://mlsanity.com/paper/1908.09511/) (2019)
- [Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2003.07493/) (2020)
- [SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning](https://mlsanity.com/paper/2008.00975/) (2020)
- [Joint Contrastive Learning with Infinite Possibilities](https://mlsanity.com/paper/2009.14776/) (2020)
- [Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping](https://mlsanity.com/paper/1807.03547/) (2018)
- [Learning a Unified Sample Weighting Network for Object Detection](https://mlsanity.com/paper/2006.06568/) (2020)
- [Pyramid Mask Text Detector](https://mlsanity.com/paper/1903.11800/) (2019)

## Built on by (most cited first, 4 of 4)

- [Relation DETR: Exploring Explicit Position Relation Prior for Object Detection](https://mlsanity.com/paper/2407.11699/) (2024)
- [Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation](https://mlsanity.com/paper/2506.17891/) (2025)
- [LP-DETR: Layer-wise Progressive Relations for Object Detection](https://mlsanity.com/paper/2502.05147/) (2025)
- [RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors](https://mlsanity.com/paper/2507.21567/) (2025)

## Abstract (arXiv)

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: urlhttps://github.com/jylins/CORE-Text.