Salvato in:
Dettagli Bibliografici
Autori principali: Simon, Tom, Nicolas, Stephane, Tranouez, Pierrick, Chatelain, Clement, Paquet, Thierry
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.29450
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911556678189056
author Simon, Tom
Nicolas, Stephane
Tranouez, Pierrick
Chatelain, Clement
Paquet, Thierry
author_facet Simon, Tom
Nicolas, Stephane
Tranouez, Pierrick
Chatelain, Clement
Paquet, Thierry
contents While state-of-the-art Handwritten Text Recognition (HTR) models perform well on standard benchmarks, they frequently struggle with writers exhibiting highly specific styles that are underrepresented in the training data. To handle unseen and atypical writers, writer adaptation techniques personalize HTR models to individual handwriting styles. Leading writer adaptation methods require either offline fine-tuning or parameter updates at inference time, both involving gradient computation and backpropagation, which increase computational costs and demand careful hyperparameter tuning. In this work, we propose a novel context-driven HTR framework3 inspired by multimodal in-context learning, enabling inference-time writer adaptation using only a few examples from the target writer without any parameter updates. We further demonstrate the impact of context length, design a compact 8M-parameter CNN-Transformer that enables few-shot in-context adaptation, and show that combining context-driven and standard OCR training strategies leads to complementary improvements. Experiments on IAM and RIMES validate our approach with Character Error Rates of 3.92% and 2.34%, respectively, surpassing all writer-independent HTR models without requiring any parameter updates at inference time.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29450
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Few-shot Writer Adaptation via Multimodal In-Context Learning
Simon, Tom
Nicolas, Stephane
Tranouez, Pierrick
Chatelain, Clement
Paquet, Thierry
Computer Vision and Pattern Recognition
Artificial Intelligence
While state-of-the-art Handwritten Text Recognition (HTR) models perform well on standard benchmarks, they frequently struggle with writers exhibiting highly specific styles that are underrepresented in the training data. To handle unseen and atypical writers, writer adaptation techniques personalize HTR models to individual handwriting styles. Leading writer adaptation methods require either offline fine-tuning or parameter updates at inference time, both involving gradient computation and backpropagation, which increase computational costs and demand careful hyperparameter tuning. In this work, we propose a novel context-driven HTR framework3 inspired by multimodal in-context learning, enabling inference-time writer adaptation using only a few examples from the target writer without any parameter updates. We further demonstrate the impact of context length, design a compact 8M-parameter CNN-Transformer that enables few-shot in-context adaptation, and show that combining context-driven and standard OCR training strategies leads to complementary improvements. Experiments on IAM and RIMES validate our approach with Character Error Rates of 3.92% and 2.34%, respectively, surpassing all writer-independent HTR models without requiring any parameter updates at inference time.
title Few-shot Writer Adaptation via Multimodal In-Context Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.29450