# Relaxed syntax modeling in Transformers for future-proof license plate recognition

arXiv: https://arxiv.org/abs/2506.17051 · HTML: https://mlsanity.com/paper/2506.17051/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis](https://mlsanity.com/paper/1701.02096/) (2017)
- [DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition](https://mlsanity.com/paper/2203.12273/) (2022)
- [SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models](https://mlsanity.com/paper/2107.09313/) (2021)
- [On Vocabulary Reliance in Scene Text Recognition](https://mlsanity.com/paper/2005.03959/) (2020)
- [An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detector](https://mlsanity.com/paper/1909.01754/) (2019)
- [Improving Zero-Shot Translation by Disentangling Positional Information](https://mlsanity.com/paper/2012.15127/) (2020)
- [A Robust Attentional Framework for License Plate Recognition in the Wild](https://mlsanity.com/paper/2006.03919/) (2020)
- [Forensic License Plate Recognition with Compression-Informed Transformers](https://mlsanity.com/paper/2207.14686/) (2022)
- [MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition](https://mlsanity.com/paper/2305.14758/) (2023)
- [Relational Contrastive Learning for Scene Text Recognition](https://mlsanity.com/paper/2308.00508/) (2023)
- [I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition](https://mlsanity.com/paper/2105.08383/) (2021)
- [Improving Scene Text Recognition for Character-Level Long-Tailed Distribution](https://mlsanity.com/paper/2304.08592/) (2023)
- [Vision-Language Adaptive Mutual Decoder for OOV-STR](https://mlsanity.com/paper/2209.00859/) (2022)

## Built on by (most cited first, 1 of 1)

- [N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition](https://mlsanity.com/paper/2603.03930/) (2026)

## Abstract (arXiv)

Effective license plate recognition systems are required to be resilient to constant change, as new license plates are released into traffic daily. While Transformer-based networks excel in their recognition at first sight, we observe significant performance drop over time which proves them unsuitable for tense production environments. Indeed, such systems obtain state-of-the-art results on plates whose syntax is seen during training. Yet, we show they perform similarly to random guessing on future plates where legible characters are wrongly recognized due to a shift in their syntax. After highlighting the flows of positional and contextual information in Transformer encoder-decoders, we identify several causes for their over-reliance on past syntax. Following, we devise architectural cut-offs and replacements which we integrate into SaLT, an attempt at a Syntax-Less Transformer for syntax-agnostic modeling of license plate representations. Experiments on both real and synthetic datasets show that our approach reaches top accuracy on past syntax and most importantly nearly maintains performance on future license plates. We further demonstrate the robustness of our architecture enhancements by way of various ablations.