# Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning

arXiv: https://arxiv.org/abs/1908.09990 · HTML: https://mlsanity.com/paper/1908.09990/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2019.

## Built on by (most cited first, 11 of 11)

- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation](https://mlsanity.com/paper/2110.12826/) (2021)
- [Dense Semantic Contrast for Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2109.07756/) (2021)
- [Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection](https://mlsanity.com/paper/2109.03426/) (2021)
- [Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning](https://mlsanity.com/paper/2308.07202/) (2023)
- [Text Growing on Leaf](https://mlsanity.com/paper/2209.03016/) (2022)
- [MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification](https://mlsanity.com/paper/2107.00808/) (2021)
- [Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images](https://mlsanity.com/paper/2109.03451/) (2021)
- [UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection](https://mlsanity.com/paper/2205.04683/) (2022)
- [SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting](https://mlsanity.com/paper/2504.09966/) (2025)
- [Towards Training-Free Scene Text Editing](https://mlsanity.com/paper/2603.24571/) (2026)

## Abstract (arXiv)

Detecting curved text in the wild is very challenging. Recently, most state-of-the-art methods are segmentation based and require pixel-level annotations. We propose a novel scheme to train an accurate text detector using only a small amount of pixel-level annotated data and a large amount of data annotated with rectangles or even unlabeled data. A baseline model is first obtained by training with the pixel-level annotated data and then used to annotate unlabeled or weakly labeled data. A novel strategy which utilizes ground-truth bounding boxes to generate pseudo mask annotations is proposed in weakly-supervised learning. Experimental results on CTW1500 and Total-Text demonstrate that our method can substantially reduce the requirement of pixel-level annotated data. Our method can also generalize well across two datasets. The performance of the proposed method is comparable with the state-of-the-art methods with only 10% pixel-level annotated data and 90% rectangle-level weakly annotated data.