# Weakly Supervised Scene Text Detection using Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2201.04866 · HTML: https://mlsanity.com/paper/2201.04866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 13 Jan 2022.

## Builds on (most cited first, 29 of 29)

- [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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Arbitrary-Oriented Scene Text Detection via Rotation Proposals](https://mlsanity.com/paper/1703.01086/) (2017)
- [Shape Robust Text Detection with Progressive Scale Expansion Network](https://mlsanity.com/paper/1903.12473/) (2019)
- [ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019](https://mlsanity.com/paper/1907.00945/) (2019)
- [TextBoxes: A Fast Text Detector with a Single Deep Neural Network](https://mlsanity.com/paper/1611.06779/) (2016)
- [TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://mlsanity.com/paper/1807.01544/) (2018)
- [Detecting Text in Natural Image with Connectionist Text Proposal Network](https://mlsanity.com/paper/1609.03605/) (2016)
- [ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection](https://mlsanity.com/paper/2004.04940/) (2020)
- [R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection](https://mlsanity.com/paper/1706.09579/) (2017)
- [Active Object Localization with Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06015/) (2015)
- [Reinforcement Learning with Latent Flow](https://mlsanity.com/paper/2101.01857/) (2021)
- [Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation](https://mlsanity.com/paper/1911.09026/) (2019)
- [Hierarchical Object Detection with Deep Reinforcement Learning](https://mlsanity.com/paper/1611.03718/) (2016)
- [Tree-Structured Reinforcement Learning for Sequential Object Localization](https://mlsanity.com/paper/1703.02710/) (2017)
- [Collaborative Deep Reinforcement Learning for Joint Object Search](https://mlsanity.com/paper/1702.05573/) (2017)
- [Tightness-aware Evaluation Protocol for Scene Text Detection](https://mlsanity.com/paper/1904.00813/) (2019)
- [Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding](https://mlsanity.com/paper/1905.10622/) (2019)
- [Modern Deep Reinforcement Learning Algorithms](https://mlsanity.com/paper/1906.10025/) (2019)
- [Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network](https://mlsanity.com/paper/1603.09423/) (2016)
- [DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images](https://mlsanity.com/paper/1605.07314/) (2016)
- [Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images](https://mlsanity.com/paper/1912.00384/) (2019)
- [Weakly-Supervised Arbitrary-Shaped Text Detection with Expectation-Maximization Algorithm](https://mlsanity.com/paper/2012.00424/) (2020)
- [LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks](https://mlsanity.com/paper/1811.05773/) (2018)
- [A Survey of Reinforcement Learning Techniques: Strategies, Recent Development, and Future Directions](https://mlsanity.com/paper/2001.06921/) (2020)

## Abstract (arXiv)

The challenging field of scene text detection requires complex data annotation, which is time-consuming and expensive. Techniques, such as weak supervision, can reduce the amount of data needed. In this paper we propose a weak supervision method for scene text detection, which makes use of reinforcement learning (RL). The reward received by the RL agent is estimated by a neural network, instead of being inferred from ground-truth labels. First, we enhance an existing supervised RL approach to text detection with several training optimizations, allowing us to close the performance gap to regression-based algorithms. We then use our proposed system in a weakly- and semi-supervised training on real-world data. Our results show that training in a weakly supervised setting is feasible. However, we find that using our model in a semi-supervised setting , e.g. when combining labeled synthetic data with unannotated real-world data, produces the best results.