SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels
Not on the map. Why?
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 51 references that are in the map. First posted on arXiv 5 Dec 2022.
Builds on
21 of 51 references.
References · 21
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
- 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
- 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
- 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
- 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
- 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
- 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
9 more
- 2020Meta Pseudo Labelscited by 372
- 2014Learning with Pseudo-Ensemblescited by 241
- 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
- 2016Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognitioncited by 33
- 2020Semi-Supervised Learning with Data Augmentation for End-to-End ASRcited by 19
- 2022Multimodal Semi-Supervised Learning for Text Recognitioncited by 16
- 2021AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptionscited by 10
- 2022Pushing the Performance Limit of Scene Text Recognizer without Human Annotationcited by 7
- 2022Self-Training of Handwritten Word Recognition for Synthetic-to-Real Adaptationcited by 5
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.