# Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild

arXiv: https://arxiv.org/abs/2009.01766 · HTML: https://mlsanity.com/paper/2009.01766/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2020.

## Built on by (most cited first, 15 of 15)

- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [Turning a CLIP Model into a Scene Text Detector](https://mlsanity.com/paper/2302.14338/) (2023)
- [A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension](https://mlsanity.com/paper/2305.03347/) (2023)
- [Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting](https://mlsanity.com/paper/2203.03911/) (2022)
- [End-to-End Video Text Spotting with Transformer](https://mlsanity.com/paper/2203.10539/) (2022)
- [Explore Faster Localization Learning For Scene Text Detection](https://mlsanity.com/paper/2207.01342/) (2022)
- [FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation](https://mlsanity.com/paper/2305.03327/) (2023)
- [Turning a CLIP Model into a Scene Text Spotter](https://mlsanity.com/paper/2308.10408/) (2023)
- [Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors](https://mlsanity.com/paper/2312.05286/) (2023)
- [Real-time End-to-End Video Text Spotter with Contrastive Representation Learning](https://mlsanity.com/paper/2207.08417/) (2022)
- [DSText V2: A Comprehensive Video Text Spotting Dataset for Dense and Small Text](https://mlsanity.com/paper/2312.01938/) (2023)
- [UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection](https://mlsanity.com/paper/2205.04683/) (2022)
- [Domain Adaptive Scene Text Detection via Subcategorization](https://mlsanity.com/paper/2212.00377/) (2022)
- [Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance](https://mlsanity.com/paper/2310.00917/) (2023)
- [VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization](https://mlsanity.com/paper/2404.19652/) (2024)

## Abstract (arXiv)

Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are unavailable. Exploiting synthetic data is a very promising solution except for domain distribution mismatches between synthetic datasets and real datasets. To address the severe domain distribution mismatch, we propose a synthetic-to-real domain adaptation method for scene text detection, which transfers knowledge from synthetic data (source domain) to real data (target domain). In this paper, a text self-training (TST) method and adversarial text instance alignment (ATA) for domain adaptive scene text detection are introduced. ATA helps the network learn domain-invariant features by training a domain classifier in an adversarial manner. TST diminishes the adverse effects of false positives~(FPs) and false negatives~(FNs) from inaccurate pseudo-labels. Two components have positive effects on improving the performance of scene text detectors when adapting from synthetic-to-real scenes. We evaluate the proposed method by transferring from SynthText, VISD to ICDAR2015, ICDAR2013. The results demonstrate the effectiveness of the proposed method with up to 10% improvement, which has important exploration significance for domain adaptive scene text detection. Code is available at https://github.com/weijiawu/SyntoReal_STD