# Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation

arXiv: https://arxiv.org/abs/1911.09026 · HTML: https://mlsanity.com/paper/1911.09026/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2019.

## Built on by (most cited first, 14 of 14)

- [TextStyleBrush: Transfer of Text Aesthetics from a Single Example](https://mlsanity.com/paper/2106.08385/) (2021)
- [Visual Text Processing: A Comprehensive Review and Unified Evaluation](https://mlsanity.com/paper/2504.21682/) (2025)
- [FETNet: Feature Erasing and Transferring Network for Scene Text Removal](https://mlsanity.com/paper/2306.09593/) (2023)
- [UPOCR: Towards Unified Pixel-Level OCR Interface](https://mlsanity.com/paper/2312.02694/) (2023)
- [A multi-stage GAN for multi-organ chest X-ray image generation and segmentation](https://mlsanity.com/paper/2106.05132/) (2021)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data](https://mlsanity.com/paper/2209.02397/) (2022)
- [WAS: Dataset and Methods for Artistic Text Segmentation](https://mlsanity.com/paper/2408.00106/) (2024)
- [Weakly-Supervised Text Instance Segmentation](https://mlsanity.com/paper/2303.10848/) (2023)
- [Leverage Weakly Annotation to Pixel-wise Annotation via Zero-shot Segment Anything Model for Molecular-empowered Learning](https://mlsanity.com/paper/2308.05785/) (2023)
- [EAFormer: Scene Text Segmentation with Edge-Aware Transformers](https://mlsanity.com/paper/2407.17020/) (2024)
- [Self-supervised Scene Text Segmentation with Object-centric Layered Representations Augmented by Text Regions](https://mlsanity.com/paper/2308.13178/) (2023)
- [Weakly Supervised Scene Text Detection using Deep Reinforcement Learning](https://mlsanity.com/paper/2201.04866/) (2022)
- [Learning Attribute-aware Representations for Few-shot Scene Text Segmentation](https://mlsanity.com/paper/2504.11164/) (2025)

## Abstract (arXiv)

Providing pixel-level supervisions for scene text segmentation is inherently difficult and costly, so that only few small datasets are available for this task. To face the scarcity of training data, previous approaches based on Convolutional Neural Networks (CNNs) rely on the use of a synthetic dataset for pre-training. However, synthetic data cannot reproduce the complexity and variability of natural images. In this work, we propose to use a weakly supervised learning approach to reduce the domain-shift between synthetic and real data. Leveraging the bounding-box supervision of the COCO-Text and the MLT datasets, we generate weak pixel-level supervisions of real images. In particular, the COCO-Text-Segmentation (COCO_TS) and the MLT-Segmentation (MLT_S) datasets are created and released. These two datasets are used to train a CNN, the Segmentation Multiscale Attention Network (SMANet), which is specifically designed to face some peculiarities of the scene text segmentation task. The SMANet is trained end-to-end on the proposed datasets, and the experiments show that COCO_TS and MLT_S are a valid alternative to synthetic images, allowing to use only a fraction of the training samples and improving significantly the performances.