cs.CVNov 13, 2026

DRA-HTR: Disentangling Representation and Adaptation for Handwritten Text Recognition

Authors: Gayan H. Pathirage, Florent Imbert, Denis Coquenet, Elisa H. Barney Smith

Organizations: 1Machine Learning Group, Lule˚a University of Technology, Lule˚a, Sweden. · 2Univ Rennes, CNRS, IRISA - UMR 6074, F-35000 Rennes, France.

Abstract

Handwritten text recognition (HTR), particularly when applied to historical documents, remains challenging due to the scarcity of annotated data and the substantial domain shifts caused by variations in handwriting styles, document degradation, acquisition conditions, and linguistic characteristics. While large amounts of unlabeled target-domain data are often available, effectively exploiting them requires adaptation strategies tailored to the specific requirements of HTR. We propose DRA-HTR, an unsupervised generative domain adaptation pipeline specifically designed for HTR and built upon the DRANet framework. The proposed approach combines source-domain pretraining, unsupervised adaptation to the visual characteristics of the target domain, relying on the generation of target-style source samples for task-specific training. We further investigate the integration of post-HTR correction to complement visual adaptation with language adaptation, relying on large language models, which we introduce as DRAL-HTR. The proposed framework is evaluated across seven HTR datasets spanning four languages, using a single set of hyperparameters for all source-target combinations. The recognition model achieves state-of-the-art performance on four datasets and competitive results on the remaining three. In addition, the proposed DRA-HTR establishes a new state-of-the-art for domain adaptation across all seven datasets and substantially improves overall robustness and training stability compared to the original DRANet framework: it reduces the Character Error Rate (CER) in average by 13.52 percentage points, and the average standard deviation decreases from 7.23 to 1.11 percentage points. Finally, post-HTR correction further reduces the CER by 2.16 percentage points.

Figures & tables

Explore similar work

CardsList
  1. Domain Adaptation Based Pipeline for Character Classification and Handwritten Text Recognition

    Nov 13, 2026Florent Imbert, Simon Corbillé, Hui Han +1Optical Character RecognitionDomain Adaptation

  2. TrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation

    Jun 23, 2026Sachin Sharma, Michele Flammini, Federico SimonettaFine-TuningVLM Adaptation

  3. Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies

    Apr 8, 2026Carlos Garrido-Munoz, Aniello Panariello, Silvia Cascianelli +4Synthetic-to-Real Domain AdaptationTransfer Learning