Papers › Vision Transformer for Fast and Efficient Scene Text Recognition

Vision Transformer for Fast and Efficient Scene Text Recognition

18 May 2021arXiv:2105.08582archive 2025-07-28

Rowel Atienza

Scene text recognition (STR) enables computers to read text in natural scenes such as object labels, road signs and instructions. STR helps machines perform informed decisions such as what object to pick, which direction to go, and what is the next step of action. In the body of work on STR, the focus has always been on recognition accuracy. There is little emphasis placed on speed and computational efficiency which are equally important especially for energy-constrained mobile machines. In this paper we propose ViTSTR, an STR with a simple single stage model architecture built on a compute and parameter efficient vision transformer (ViT). On a comparable strong baseline method such as TRBA with accuracy of 84.3%, our small ViTSTR achieves a competitive accuracy of 82.6% (84.2% with data augmentation) at 2.4x speed up, using only 43.4% of the number of parameters and 42.2% FLOPS. The tiny version of ViTSTR achieves 80.3% accuracy (82.1% with data augmentation), at 2.5x the speed, requiring only 10.9% of the number of parameters and 11.9% FLOPS. With data augmentation, our base ViTSTR outperforms TRBA at 85.2% accuracy (83.7% without augmentation) at 2.3x the speed but requires 73.2% more parameters and 61.5% more FLOPS. In terms of trade-offs, nearly all ViTSTR configurations are at or near the frontiers to maximize accuracy, speed and computational efficiency all at the same time.

PaperPDFCode

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

Code

roatienza/deep-text-recognition-benchmark officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
Eom-taeseon/CV_SceneTextRecognition mentioned on GitHubpytorchApache-2.0 report
PaddlePaddle/PaddleOCR paddleApache-2.0 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

Computational EfficiencyData AugmentationScene Text Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Recognition ICDAR 2003 ViTSTR Accuracy 94.3 #8 of 12 Archive leaderboard report
Scene Text Recognition ICDAR2013 ViTSTR Accuracy 92.4 #30 of 38 Archive leaderboard report
Scene Text Recognition ICDAR2015 ViTSTR Accuracy 72.6 #25 of 27 Archive leaderboard report
Scene Text Recognition SVT ViTSTR Accuracy 87.7 #30 of 37 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

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision 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