Skip to main content
SpringerLink
Log in

Accelerating Transformer-Based Scene Text Detection and Recognition via Token Pruning

  • Conference paper
  • First Online:
Document Analysis and Recognition - ICDAR 2023 (ICDAR 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14192))

Included in the following conference series:

Abstract

Scene text detection and recognition is a crucial task in computer vision with numerous real-world applications. Transformer-based approaches are behind all current state-of-the-art models and have achieved excellent performance. However, the computational requirements of the transformer architecture makes training these methods slow and resource heavy. In this paper, we introduce a new token pruning strategy that significantly decreases training and inference times without sacrificing performance, striking a balance between accuracy and speed. We have applied this pruning technique to our own end-to-end transformer-based scene text understanding architecture. Our method uses a separate detection branch to guide the pruning of uninformative image features, which significantly reduces the number of tokens at the input of the transformer. Experimental results show how our network is able to obtain competitive results on multiple public benchmarks while running at significantly higher speeds.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3286–3295 (2019)

    Google Scholar 

  2. Biten, A.F., et al.: Scene text visual question answering. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4291–4301 (2019)

    Google Scholar 

  3. Ch’ng, C.K., Chan, C.S.: Total-text: a comprehensive dataset for scene text detection and recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 935–942. IEEE (2017)

    Google Scholar 

  4. Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)

  5. Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)

  6. Fayyaz, M., et al.: Adaptive token sampling for efficient vision transformers. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13671, pp. 396–414. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20083-0_24

  7. Feng, W., He, W., Yin, F., Zhang, X.Y., Liu, C.-L.: Textdragon: an end-to-end framework for arbitrary shaped text spotting. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9076–9085 (2019)

    Google Scholar 

  8. Gómez, L., Rusinol, M., Karatzas, D.: Cutting sayre’s knot: reading scene text without segmentation. application to utility meters. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 97–102. IEEE (2018)

    Google Scholar 

  9. Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369–376 (2006)

    Google Scholar 

  10. Guo, Q., Qiu, X., Liu, P., Shao, Y., Xue, X., Zhang, Z.: Star-transformer. arXiv preprint arXiv:1902.09113 (2019)

  11. He, T., Tian, Z., Huang, W., Shen, C., Qiao, Y., Sun, C.: An end-to-end textspotter with explicit alignment and attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5020–5029 (2018)

    Google Scholar 

  12. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)

    Article  Google Scholar 

  13. Huang, M., et al.: Swintextspotter: scene text spotting via better synergy between text detection and text recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4593–4603 (2022)

    Google Scholar 

  14. Jaszczur, S., et al.: Sparse is enough in scaling transformers. Adv. Neural Inf. Process. Syst. 34, 9895–9907 (2021)

    Google Scholar 

  15. Jiao, X., et al.: Tinybert: distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)

  16. Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156–1160. IEEE (2015)

    Google Scholar 

  17. Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484–1493. IEEE (2013)

    Google Scholar 

  18. Kim, S., et al.: Deer: detection-agnostic end-to-end recognizer for scene text spotting. arXiv preprint arXiv:2203.05122 (2022)

  19. Kittenplon, Y., Lavi, I., Fogel, S., Bar, Y., Manmatha, R., Perona, P.: Towards weakly-supervised text spotting using a multi-task transformer. arXiv preprint arXiv:2202.05508 (2022)

  20. Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 734–750 (2018)

    Google Scholar 

  21. Lee, C.-Y., Osindero, S.: Recursive recurrent nets with attention modeling for OCR in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2231–2239 (2016)

    Google Scholar 

  22. Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: expediting vision transformers via token reorganizations. arXiv preprint arXiv:2202.07800 (2022)

  23. Liao, M., Pang, G., Huang, J., Hassner, T., Bai, X.: Mask TextSpotter v3: segmentation proposal network for robust scene text spotting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 706–722. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_41

    Chapter  Google Scholar 

  24. Liao, M., Shi, B., Bai, X.: Textboxes++: a single-shot oriented scene text detector. IEEE Trans. Image Process. 27(8), 3676–3690 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  25. Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)

    Google Scholar 

  26. Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

    Google Scholar 

  27. Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., Yan, J.: Fots: fast oriented text spotting with a unified network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5676–5685 (2018)

    Google Scholar 

  28. Liu, Y., Chen, H., Shen, C., He, T., Jin, L., Wang, L.: Abcnet: real-time scene text spotting with adaptive bezier-curve network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9809–9818 (2020)

    Google Scholar 

  29. Liu, Y., Jin, L., Zhang, S., Luo, C., Zhang, S.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recogn. 90, 337–345 (2019)

    Article  Google Scholar 

  30. Liu, Y., et al.: Abcnet v2: adaptive bezier-curve network for real-time end-to-end text spotting. arXiv preprint arXiv:2105.03620 (2021)

  31. Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)

  32. Lyu, P., Liao, M., Yao, C., Wu, W., Bai, X.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 67–83 (2018)

    Google Scholar 

  33. Mafla, A., Dey, S., Biten, A.F., Gomez, L., Karatzas, D.: Fine-grained image classification and retrieval by combining visual and locally pooled textual features. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2950–2959 (2020)

    Google Scholar 

  34. Nayef, N., et al.: ICDAR 2017 robust reading challenge on multi-lingual scene text detection and script identification-RRC-MLT. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1454–1459. IEEE (2017)

    Google Scholar 

  35. Pan, B., et al.: IA-RED\(^{2}\): interpretability-aware redundancy reduction for vision transformers. Adv. Neural Inf. Process. Syst. 34, 24898–24911 (2021)

    MathSciNet  Google Scholar 

  36. Pan, Z., Zhuang, B., Liu, J., He, H., Cai, J.: Scalable vision transformers with hierarchical pooling. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 377–386 (2021)

    Google Scholar 

  37. Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055–4064. PMLR (2018)

    Google Scholar 

  38. Peng, D., et al. Spts: single-point text spotting. arXiv preprint arXiv:2112.07917 (2021)

  39. Qiao, L., et al.: Mango: a mask attention guided one-stage scene text spotter. arXiv preprint arXiv:2012.04350 (2020)

  40. Qiao, L., et al.: Text perceptron: towards end-to-end arbitrary-shaped text spotting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11899–11907 (2020)

    Google Scholar 

  41. Rao, Y., Zhao, W., Liu, B., Jiwen, L., Zhou, J., Hsieh, C.-J.: Dynamicvit: efficient vision transformers with dynamic token sparsification. Adv. Neural Inf. Process. Syst. 34, 13937–13949 (2021)

    Google Scholar 

  42. Reddy, S., Mathew, M., Gomez, L., Rusinol, M., Karatzas, D., Jawahar, C.V.: Roadtext-1k: text detection & recognition dataset for driving videos. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 11074–11080. IEEE (2020)

    Google Scholar 

  43. Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  44. Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Sig. Process. 45(11), 2673–2681 (1997)

    Google Scholar 

  45. Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317–8326 (2019)

    Google Scholar 

  46. Singh, A., Pang, G., Toh, M., Huang, J., Galuba, W., Hassner, T.: Textocr: towards large-scale end-to-end reasoning for arbitrary-shaped scene text. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8802–8812 (2021)

    Google Scholar 

  47. Vaswani, A., et al: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)

    Google Scholar 

  48. Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)

  49. Wang, H., et al.: All you need is boundary: toward arbitrary-shaped text spotting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12160–12167 (2020)

    Google Scholar 

  50. Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)

  51. Xing, L., Tian, Z., Huang, W., Scott, M.R.: Convolutional character networks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9126–9136 (2019)

    Google Scholar 

  52. Zhang, X., Su, Y., Tripathi, S., Tu, Z.: Text spotting transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9519–9528 (2022)

    Google Scholar 

  53. Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)

Download references

Acknowledgements

This work has been supported by grants PDC2021-121512-I00, PID2020-116298GB-I00 and PLEC2021-007850 funded by the European Union NextGenerationEU/PRTR and MCIN/AEI/10.13039/501100011033; the EU Lighthouse on Safe and Secure AI - ELSA funded by European Union’s Horizon Europe programme under grant agreement No 101070617; the Spanish Project NEOTEC SNEO-20211172 from CDTI; grant Torres Quevedo PTQ2019-010662; and the Industrial Doctorate programme of the Catalan Government (2020 DI 058).

Author information

Authors and Affiliations

  1. Computer Vision Center, Universitat Autonoma de Barcelona, Barcelona, Spain

    Sergi Garcia-Bordils & Dimosthenis Karatzas

  2. AllRead MLT, Barcelona, Spain

    Sergi Garcia-Bordils & Marçal Rusiñol

Authors
  1. Sergi Garcia-Bordils
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dimosthenis Karatzas
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marçal Rusiñol
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sergi Garcia-Bordils .

Editor information

Editors and Affiliations

  1. TU Dortmund University, Dortmund, Germany

    Gernot A. Fink

  2. Adobe, College Park, MN, USA

    Rajiv Jain

  3. Osaka Metropolitan University, Osaka, Japan

    Koichi Kise

  4. Rochester Institute of Technology, Rochester, NY, USA

    Richard Zanibbi

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Garcia-Bordils, S., Karatzas, D., Rusiñol, M. (2023). Accelerating Transformer-Based Scene Text Detection and Recognition via Token Pruning. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds) Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. Lecture Notes in Computer Science, vol 14192. Springer, Cham. https://doi.org/10.1007/978-3-031-41731-3_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-41731-3_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-41730-6

  • Online ISBN: 978-3-031-41731-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation