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

arXiv: https://arxiv.org/abs/2212.02135 · HTML: https://mlsanity.com/paper/2212.02135/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 5 Dec 2022.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels](https://mlsanity.com/paper/2105.04522/) (2021)
- [Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1610.09975/) (2016)
- [Semi-Supervised Learning with Data Augmentation for End-to-End ASR](https://mlsanity.com/paper/2007.13876/) (2020)
- [Multimodal Semi-Supervised Learning for Text Recognition](https://mlsanity.com/paper/2205.03873/) (2022)
- [AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions](https://mlsanity.com/paper/2104.13037/) (2021)
- [Pushing the Performance Limit of Scene Text Recognizer without Human Annotation](https://mlsanity.com/paper/2204.07714/) (2022)
- [Self-Training of Handwritten Word Recognition for Synthetic-to-Real Adaptation](https://mlsanity.com/paper/2206.03149/) (2022)

## Built on by (most cited first, 2 of 2)

- [Self-supervised Pre-training of Text Recognizers](https://mlsanity.com/paper/2405.00420/) (2024)
- [Masked Self-Supervised Pre-Training for Text Recognition Transformers on Large-Scale Datasets](https://mlsanity.com/paper/2503.22513/) (2025)

## Abstract (arXiv)

This paper explores semi-supervised training for sequence tasks, such as Optical Character Recognition or Automatic Speech Recognition. We propose a novel loss function unicodex2013 SoftCTC unicodex2013 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.