# SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition

arXiv: https://arxiv.org/abs/2202.11949 · HTML: https://mlsanity.com/paper/2202.11949/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 24 Feb 2022.

## Builds on (most cited first, 15 of 15)

- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [Robust Scene Text Recognition with Automatic Rectification](https://mlsanity.com/paper/1603.03915/) (2016)
- [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://mlsanity.com/paper/1709.02054/) (2017)
- [GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition](https://mlsanity.com/paper/1907.09653/) (2019)
- [Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment](https://mlsanity.com/paper/2006.12770/) (2020)
- [Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition](https://mlsanity.com/paper/2111.13327/) (2021)

## Built on by (most cited first, 2 of 2)

- [Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition](https://mlsanity.com/paper/2410.09913/) (2024)
- [Leveraging Audio Representations for Vibration-Based Crowd Monitoring in Stadiums](https://mlsanity.com/paper/2503.17646/) (2025)

## Abstract (arXiv)

Training recognition models with synthetic images have achieved remarkable results in text recognition. However, recognizing text from real-world images still faces challenges due to the domain shift between synthetic and real-world text images. One of the strategies to eliminate the domain difference without manual annotation is unsupervised domain adaptation (UDA). Due to the characteristic of sequential labeling tasks, most popular UDA methods cannot be directly applied to text recognition. To tackle this problem, we proposed a UDA method with minimizing latent entropy on sequence-to-sequence attention-based models with classbalanced self-paced learning. Our experiments show that our proposed framework achieves better recognition results than the existing methods on most UDA text recognition benchmarks. All codes are publicly available.