# DOTA: Deformable Optimized Transformer Architecture for End-to-End Text Recognition with Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2505.04175 · HTML: https://mlsanity.com/paper/2505.04175/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 7 May 2025.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 21 of 21)

- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (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)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes](https://mlsanity.com/paper/1908.08207/) (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)
- [SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://mlsanity.com/paper/2005.10977/) (2020)
- [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://mlsanity.com/paper/1709.02054/) (2017)
- [Decoupled Attention Network for Text Recognition](https://mlsanity.com/paper/1912.10205/) (2019)
- [From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network](https://mlsanity.com/paper/2108.09661/) (2021)
- [RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition](https://mlsanity.com/paper/2007.07542/) (2020)
- [ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification](https://mlsanity.com/paper/1812.05824/) (2018)
- [NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition](https://mlsanity.com/paper/1806.00926/) (2018)
- [TextScanner: Reading Characters in Order for Robust Scene Text Recognition](https://mlsanity.com/paper/1912.12422/) (2019)
- [DTrOCR: Decoder-only Transformer for Optical Character Recognition](https://mlsanity.com/paper/2308.15996/) (2023)
- [Primitive Representation Learning for Scene Text Recognition](https://mlsanity.com/paper/2105.04286/) (2021)
- [Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition](https://mlsanity.com/paper/2112.12916/) (2021)
- [Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition](https://mlsanity.com/paper/2107.12090/) (2021)
- [2D Attentional Irregular Scene Text Recognizer](https://mlsanity.com/paper/1906.05708/) (2019)
- [Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images](https://mlsanity.com/paper/2212.05525/) (2022)

## Abstract (arXiv)

Text recognition in natural images remains a challenging yet essential task, with broad applications spanning computer vision and natural language processing. This paper introduces a novel end-to-end framework that combines ResNet and Vision Transformer backbones with advanced methodologies, including Deformable Convolutions, Retrieval-Augmented Generation, and Conditional Random Fields (CRF). These innovations collectively enhance feature representation and improve Optical Character Recognition (OCR) performance. Specifically, the framework substitutes standard convolution layers in the third and fourth blocks with Deformable Convolutions, leverages adaptive dropout for regularization, and incorporates CRF for more refined sequence modeling. Extensive experiments conducted on six benchmark datasets IC13, IC15, SVT, IIIT5K, SVTP, and CUTE80 validate the proposed method's efficacy, achieving notable accuracies: 97.32% on IC13, 58.26% on IC15, 88.10% on SVT, 74.13% on IIIT5K, 82.17% on SVTP, and 66.67% on CUTE80, resulting in an average accuracy of 77.77%. These results establish a new state-of-the-art for text recognition, demonstrating the robustness of the approach across diverse and challenging datasets.