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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
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)
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)
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)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
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
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)
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)
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)
Guo, Q., Qiu, X., Liu, P., Shao, Y., Xue, X., Zhang, Z.: Star-transformer. arXiv preprint arXiv:1902.09113 (2019)
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)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
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)
Jaszczur, S., et al.: Sparse is enough in scaling transformers. Adv. Neural Inf. Process. Syst. 34, 9895–9907 (2021)
Jiao, X., et al.: Tinybert: distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)
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)
Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484–1493. IEEE (2013)
Kim, S., et al.: Deer: detection-agnostic end-to-end recognizer for scene text spotting. arXiv preprint arXiv:2203.05122 (2022)
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)
Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 734–750 (2018)
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)
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)
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
Liao, M., Shi, B., Bai, X.: Textboxes++: a single-shot oriented scene text detector. IEEE Trans. Image Process. 27(8), 3676–3690 (2018)
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)
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)
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)
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)
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)
Liu, Y., et al.: Abcnet v2: adaptive bezier-curve network for real-time end-to-end text spotting. arXiv preprint arXiv:2105.03620 (2021)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
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)
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)
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)
Pan, B., et al.: IA-RED\(^{2}\): interpretability-aware redundancy reduction for vision transformers. Adv. Neural Inf. Process. Syst. 34, 24898–24911 (2021)
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)
Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055–4064. PMLR (2018)
Peng, D., et al. Spts: single-point text spotting. arXiv preprint arXiv:2112.07917 (2021)
Qiao, L., et al.: Mango: a mask attention guided one-stage scene text spotter. arXiv preprint arXiv:2012.04350 (2020)
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)
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)
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)
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
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Sig. Process. 45(11), 2673–2681 (1997)
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)
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)
Vaswani, A., et al: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)
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)
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)
Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)
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)
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)
Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)
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
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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)