Papers › Decoupled Attention Network for Text Recognition

Decoupled Attention Network for Text Recognition

21 Dec 2019arXiv:1912.10205archive 2025-07-28

Tianwei Wang, Yuanzhi Zhu, Lianwen Jin, Canjie Luo, Xiaoxue Chen, Yaqiang Wu, Qianying Wang, Mingxiang Cai

Text recognition has attracted considerable research interests because of its various applications. The cutting-edge text recognition methods are based on attention mechanisms. However, most of attention methods usually suffer from serious alignment problem due to its recurrency alignment operation, where the alignment relies on historical decoding results. To remedy this issue, we propose a decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results. DAN is an effective, flexible and robust end-to-end text recognizer, which consists of three components: 1) a feature encoder that extracts visual features from the input image; 2) a convolutional alignment module that performs the alignment operation based on visual features from the encoder; and 3) a decoupled text decoder that makes final prediction by jointly using the feature map and attention maps. Experimental results show that DAN achieves state-of-the-art performance on multiple text recognition tasks, including offline handwritten text recognition and regular/irregular scene text recognition.

PaperPDFCode

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

Code

Canjie-Luo/Scene-Text-Image-Transformer officialmentioned in papermentioned on GitHubpytorchMIT report
Wang-Tianwei/Decoupled-attention-network officialmentioned in papermentioned on GitHubpytorch report
Canjie-Luo/Text-Image-Augmentation mentioned on GitHubpytorchMIT report
topdu/openocr mentioned on GitHubpytorchApache-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

DecoderHandwritten Text RecognitionScene Text Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Handwritten Text Recognition IAM Decouple Attention Network CER 6.4 #12 of 17 Archive leaderboard report
Handwritten Text Recognition IAM Decouple Attention Network WER 19.6 #12 of 17 Archive leaderboard report
Scene Text Recognition ICDAR 2003 DAN Accuracy 95.0 #4 of 12 Archive leaderboard report
Scene Text Recognition ICDAR2013 DAN Accuracy 93.9 #25 of 38 Archive leaderboard report
Scene Text Recognition ICDAR2015 DAN Accuracy 74.5 #23 of 27 Archive leaderboard report
Scene Text Recognition SVT DAN Accuracy 89.2 #28 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.

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