# Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation

arXiv: https://arxiv.org/abs/2107.12087 · HTML: https://mlsanity.com/paper/2107.12087/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal distillation, one of 12 directions in Knowledge distillation.
- Builds on 47 of its 67 references that are in the map.
- First posted on arXiv 26 Jul 2021.

## Placed in

- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 30 of 47)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (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)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [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)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory](https://mlsanity.com/paper/1609.02132/) (2016)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [Learning Lightweight Lane Detection CNNs by Self Attention Distillation](https://mlsanity.com/paper/1908.00821/) (2019)
- [Towards Accurate Scene Text Recognition with Semantic Reasoning Networks](https://mlsanity.com/paper/2003.12294/) (2020)
- [Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition](https://mlsanity.com/paper/1811.00751/) (2018)
- [Reading Text in the Wild with Convolutional Neural Networks](https://mlsanity.com/paper/1412.1842/) (2014)
- [Scene Text Detection and Recognition: The Deep Learning Era](https://mlsanity.com/paper/1811.04256/) (2018)
- [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://mlsanity.com/paper/1709.02054/) (2017)
- [Knowledge Adaptation for Efficient Semantic Segmentation](https://mlsanity.com/paper/1903.04688/) (2019)
- [Decoupled Attention Network for Text Recognition](https://mlsanity.com/paper/1912.10205/) (2019)
- [Multilingual Neural Machine Translation with Knowledge Distillation](https://mlsanity.com/paper/1902.10461/) (2019)
- [One Model To Learn Them All](https://mlsanity.com/paper/1706.05137/) (2017)
- [Relation Distillation Networks for Video Object Detection](https://mlsanity.com/paper/1908.09511/) (2019)
- [Recursive Recurrent Nets with Attention Modeling for OCR in the Wild](https://mlsanity.com/paper/1603.03101/) (2016)

## Built on by (most cited first, 17 of 17)

- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition](https://mlsanity.com/paper/2208.00438/) (2022)
- [Handwritten Text Generation from Visual Archetypes](https://mlsanity.com/paper/2303.15269/) (2023)
- [Self-supervised Character-to-Character Distillation for Text Recognition](https://mlsanity.com/paper/2211.00288/) (2022)
- [Self-supervised Implicit Glyph Attention for Text Recognition](https://mlsanity.com/paper/2203.03382/) (2022)
- [HWD: A Novel Evaluation Score for Styled Handwritten Text Generation](https://mlsanity.com/paper/2310.20316/) (2023)
- [VATr++: Choose Your Words Wisely for Handwritten Text Generation](https://mlsanity.com/paper/2402.10798/) (2024)
- [Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition](https://mlsanity.com/paper/2402.13643/) (2024)
- [On the Generalization of Handwritten Text Recognition Models](https://mlsanity.com/paper/2411.17332/) (2024)
- [Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach](https://mlsanity.com/paper/2308.08806/) (2023)
- [Weakly supervised information extraction from inscrutable handwritten document images](https://mlsanity.com/paper/2306.06823/) (2023)
- [Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments](https://mlsanity.com/paper/2312.15842/) (2023)
- [One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer](https://mlsanity.com/paper/2308.02770/) (2023)
- [Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting](https://mlsanity.com/paper/2207.06694/) (2022)
- [Sequential Visual and Semantic Consistency for Semi-supervised Text Recognition](https://mlsanity.com/paper/2402.15806/) (2024)
- [MOoSE: Multi-Orientation Sharing Experts for Open-set Scene Text Recognition](https://mlsanity.com/paper/2407.18616/) (2024)
- [Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation](https://mlsanity.com/paper/2503.16184/) (2025)

## Abstract (arXiv)

Text recognition remains a fundamental and extensively researched topic in computer vision, largely owing to its wide array of commercial applications. The challenging nature of the very problem however dictated a fragmentation of research efforts: Scene Text Recognition (STR) that deals with text in everyday scenes, and Handwriting Text Recognition (HTR) that tackles hand-written text. In this paper, for the first time, we argue for their unification -- we aim for a single model that can compete favourably with two separate state-of-the-art STR and HTR models. We first show that cross-utilisation of STR and HTR models trigger significant performance drops due to differences in their inherent challenges. We then tackle their union by introducing a knowledge distillation (KD) based framework. This is however non-trivial, largely due to the variable-length and sequential nature of text sequences, which renders off-the-shelf KD techniques that mostly works with global fixed-length data inadequate. For that, we propose three distillation losses all of which are specifically designed to cope with the aforementioned unique characteristics of text recognition. Empirical evidence suggests that our proposed unified model performs on par with individual models, even surpassing them in certain cases. Ablative studies demonstrate that naive baselines such as a two-stage framework, and domain adaption/generalisation alternatives do not work as well, further verifying the appropriateness of our design.