Papers › HTR-VT: Handwritten Text Recognition with Vision Transformer

HTR-VT: Handwritten Text Recognition with Vision Transformer

13 Sep 2024arXiv:2409.08573archive 2025-07-28

Yuting Li, Dexiong Chen, Tinglong Tang, Xi Shen

We explore the application of Vision Transformer (ViT) for handwritten text recognition. The limited availability of labeled data in this domain poses challenges for achieving high performance solely relying on ViT. Previous transformer-based models required external data or extensive pre-training on large datasets to excel. To address this limitation, we introduce a data-efficient ViT method that uses only the encoder of the standard transformer. We find that incorporating a Convolutional Neural Network (CNN) for feature extraction instead of the original patch embedding and employ Sharpness-Aware Minimization (SAM) optimizer to ensure that the model can converge towards flatter minima and yield notable enhancements. Furthermore, our introduction of the span mask technique, which masks interconnected features in the feature map, acts as an effective regularizer. Empirically, our approach competes favorably with traditional CNN-based models on small datasets like IAM and READ2016. Additionally, it establishes a new benchmark on the LAM dataset, currently the largest dataset with 19,830 training text lines. The code is publicly available at: https://github.com/YutingLi0606/HTR-VT.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yutingli0606/htr-vt officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

HTRHandwritten Text Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Handwritten Text Recognition IAM HTR-VT(line-level) CER 4.7 #9 of 17 Archive leaderboard report
Handwritten Text Recognition IAM HTR-VT(line-level) WER 14.9 #9 of 17 Archive leaderboard report
Handwritten Text Recognition IAM(line-level) HTR-VT Test CER 4.7 #2 of 5 Archive leaderboard report
Handwritten Text Recognition IAM(line-level) HTR-VT Test WER 14.9 #2 of 5 Archive leaderboard report
Handwritten Text Recognition LAM(line-level) HTR-VT Test CER 2.8 #1 of 6 Archive leaderboard report
Handwritten Text Recognition LAM(line-level) HTR-VT Test WER 7.4 #1 of 6 Archive leaderboard report
Handwritten Text Recognition READ 2016 HTR-VT(line-level) CER (%) 3.9 #2 of 2 Archive leaderboard report
Handwritten Text Recognition READ 2016 HTR-VT(line-level) WER (%) 16.5 #2 of 2 Archive leaderboard report
Handwritten Text Recognition READ2016(line-level) HTR-VT Test CER 3.9 #1 of 5 Archive leaderboard report
Handwritten Text Recognition READ2016(line-level) HTR-VT Test WER 16.5 #1 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSharpness-Aware MinimizationSoftmaxTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections