mlsanityData to 7 Oct 2026

Relational Contrastive Learning for Scene Text Recognition

arXiv 2308.00508 ↗First posted 1 Aug 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Context-aware methods achieved great success in supervised scene text recognition via incorporating semantic priors from words. We argue that such prior contextual information can be interpreted as the relations of textual primitives due to the heterogeneous text and background, which can provide effective self-supervised labels for representation learning. However, textual relations are restricted to the finite size of dataset due to lexical dependencies, which causes the problem of over-fitting and compromises representation robustness. To this end, we propose to enrich the textual relations via rearrangement, hierarchy and interaction, and design a unified framework called RCLSTR: Relational Contrastive Learning for Scene Text Recognition. Based on causality, we theoretically explain that three modules suppress the bias caused by the contextual prior and thus guarantee representation robustness. Experiments on representation quality show that our method outperforms state-of-the-art self-supervised STR methods. Code is available at https://github.com/ThunderVVV/RCLSTR.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 1 Aug 2023.

Builds on

35 of 53 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  12. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
23 more
  1. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  2. 2016Synthetic Data for Text Localisation in Natural Imagescited by 396
  3. 2014Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognitioncited by 214
  4. 2020Representation Learning via Invariant Causal Mechanismscited by 197
  5. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  6. 2019What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysiscited by 191
  7. 2020Towards Accurate Scene Text Recognition with Semantic Reasoning Networkscited by 131
  8. 2016Robust Scene Text Recognition with Automatic Rectificationcited by 121
  9. 2020SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognitioncited by 119
  10. 2017Focusing Attention: Towards Accurate Text Recognition in Natural Imagescited by 110
  11. 2021Contrastive Learning with Stronger Augmentationscited by 100
  12. 2021From Two to One: A New Scene Text Recognizer with Visual Language Modeling Networkcited by 97
  13. 2021ReSSL: Relational Self-Supervised Learning with Weak Augmentationcited by 83
  14. 2020Sequence-to-Sequence Contrastive Learning for Text Recognitioncited by 70
  15. 2021What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labelscited by 63
  16. 2019On Recognizing Texts of Arbitrary Shapes with 2D Self-Attentioncited by 59
  17. 2021Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Studycited by 52
  18. 2022Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognitioncited by 45
  19. 2020On Vocabulary Reliance in Scene Text Recognitioncited by 38
  20. 2020CO2: Consistent Contrast for Unsupervised Visual Representation Learningcited by 38
  21. 2020Self-Supervised Relational Reasoning for Representation Learningcited by 37
  22. 2022MaskOCR: Text Recognition with Masked Encoder-Decoder Pretrainingcited by 34
  23. 2022SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalizationcited by 21

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizercited by 4
  2. 2024Self-Supervised Learning for Text Recognition: A Critical Surveycited by 3
  3. 2025Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Modelcited by 1
  4. 2025Relaxed syntax modeling in Transformers for future-proof license plate recognitioncited by 1
  5. 2024LEGO: Self-Supervised Representation Learning for Scene Text Imagescited by 0
  6. 2024Relational Contrastive Learning and Masked Image Modeling for Scene Text Recognitioncited by 0