Papers › SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels

SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels

5 Dec 2022arXiv:2212.02135archive 2025-07-28

Martin Kišš, Michal Hradiš, Karel Beneš, Petr Buchal, Michal Kula

This paper explores semi-supervised training for sequence tasks, such as Optical Character Recognition or Automatic Speech Recognition. We propose a novel loss function x2013 SoftCTC x2013 which is an extension of CTC allowing to consider multiple transcription variants at the same time. This allows to omit the confidence based filtering step which is otherwise a crucial component of pseudo-labeling approaches to semi-supervised learning. We demonstrate the effectiveness of our method on a challenging handwriting recognition task and conclude that SoftCTC matches the performance of a finely-tuned filtering based pipeline. We also evaluated SoftCTC in terms of computational efficiency, concluding that it is significantly more efficient than a na\"ive CTC-based approach for training on multiple transcription variants, and we make our GPU implementation public.

PaperPDFCode

Code

dcgm/softctc 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

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Computational EfficiencyHandwriting RecognitionOptical Character RecognitionOptical Character Recognition (OCR)Speech Recognitionspeech-recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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