Papers › Manifold Mixup improves text recognition with CTC loss

Manifold Mixup improves text recognition with CTC loss

11 Mar 2019arXiv:1903.04246archive 2025-07-28

Bastien Moysset, Ronaldo Messina

Modern handwritten text recognition techniques employ deep recurrent neural networks. The use of these techniques is especially efficient when a large amount of annotated data is available for parameter estimation. Data augmentation can be used to enhance the performance of the systems when data is scarce. Manifold Mixup is a modern method of data augmentation that meld two images or the feature maps corresponding to these images and the targets are fused accordingly. We propose to apply the Manifold Mixup to text recognition while adapting it to work with a Connectionist Temporal Classification cost. We show that Manifold Mixup improves text recognition results on various languages and datasets.

PaperPDFCode

Code

simplify23/Ultra_light_OCR_No.11 mentioned on GitHubpaddleApache-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

Data AugmentationGeneral ClassificationHandwritten Text Recognitionparameter estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Manifold MixupMixup

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