Abstract
This chapter describes the possible approaches to implement the representation-related variable and module in the framework discussed above, i.e., the representation space and the label-to-representation mapping module. First, this chapter introduces how characters, or other corresponding granularities, are represented in different methods, i.e., the representation space, where class centers (prototypes) and features extracted from input images reside. Second, we discuss choices of human representation of labels (side-information) and different approaches in the literature to implement the label-to-representation mapping module. The module, which maps the side information to prototypes residing in the representation space, is the key to implementing class incremental learning functionality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Might have some semantic mixed in as well without explicit isolation.
- 2.
Note these methods also raise fairness concerns, for they use much more data during pretraining, which may or may not include the test images.
References
Goel, V., Mishra, A., Alahari, K., Jawahar, C.V.: Whole is greater than sum of parts: Recognizing scene text words. In: 12th International Conference on Document Analysis and Recognition. ICDAR 2013, August 25–28, pp. 398–402. IEEE Computer Society, Washington, DC, USA (2013)
Manmatha, R., Han, C., Riseman, E.M.: Word spotting: A new approach to indexing handwriting. In: 1996 Conference on Computer Vision and Pattern Recognition (CVPR ’96). June 18–20, 1996, pp. 631–637. IEEE Computer Society, San Francisco, CA, USA (1996)
Wang, K., Belongie, S.J.: Word spotting in the wild. In: Computer Vision–ECCV 2010, 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5–11, 2010, Proceedings, Part I, ser. Lecture Notes in Computer Science, vol. 6311, pp. 591–604. Springer (2010)
Almazán, J., Gordo, A., Fornés, A., Valveny, E.: Word spotting and recognition with embedded attributes. IEEE Trans. Pattern Anal. Mach. Intell. 36(12), 2552–2566 (2014)
Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298–2304 (2017)
Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: A simple and strong baseline for irregular text recognition. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27–February 1, 2019, pp. 8610–8617. AAAI Press (2019)
Xie, Z., Huang, Y., Zhu, Y., Jin, L., Liu, Y., Xie, L.: Aggregation cross-entropy for sequence recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16–20, 2019, pp. 6538–6547. Computer Vision Foundation/IEEE (2019)
Chanda, S., Baas, J., Haitink, D., Hamel, S., Stutzmann, D., Schomaker, L.: Zero-shot learning based approach for medieval word recognition using deep-learned features. In: 16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, Niagara Falls, NY, USA, August 5–8, 2018, pp. 345–350. IEEE Computer Society (2018)
Chanda, S., Haitink, D., Prasad, P.K., Baas, J., Pal, U., Schomaker, L.: Recognizing Bengali word images–A zero-shot learning perspective. In: 25th International Conference on Pattern Recognition, ICPR 2020, Virtual Event/Milan, Italy, January 10–15, 2021, pp. 5603–5610. IEEE (2020)
Rai, A., Krishnan, N.C., Chanda, S.: Pho(sc)net: An approach towards zero-shot word image recognition in historical documents. In: 16th International Conference on Document Analysis and Recognition, ICDAR 2021, Lausanne, Switzerland, September 5–10, 2021, Proceedings, Part I, ser. Lecture Notes in Computer Science, vol. 12821, pp. 19–33. Springer (2021)
Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J., Lee, H.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27–November 2, 2019, pp. 4714–4722. IEEE (2019)
Wan, Z., Zhang, J., Zhang, L., Luo, J., Yao, C.: On vocabulary reliance in scene text recognition. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13–19, 2020, pp. 11 422–11 431. IEEE (2020)
Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035–2048 (2019)
Liao, M., Zhang, J., Wan, Z., Xie, F., Liang, J., Lyu, P., Yao, C., Bai, X.: Scene text recognition from two-dimensional perspective. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27–February 1, 2019, pp. 8714–8721. AAAI Press (2019)
Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13–19, 2020, pp. 12 110–12 119. IEEE (2020)
Fang, S., Xie, H., Wang, Y., Mao, Z., Zhang, Y.: Read like humans: Autonomous, bidirectional and iterative language modeling for scene text recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19–25, 2021, pp. 7098–7107. Computer Vision Foundation/IEEE (2021)
Zhang, C., Gupta, A., Zisserman, A.: Adaptive text recognition through visual matching. In: Computer Vision–ECCV 2020–16th European Conference, Glasgow, UK, August 23–28, Proceedings, Part XVI, ser. Lecture Notes in Computer Science, vol. 12361, pp. 51–67. Springer (2020)
Souibgui, M.A., Fornés, A., Kessentini, Y., Megyesi, B.: Few shots is all you need: A progressive few shot learning approach for low resource handwriting recognition (2021). [Online]. Available: https://arxiv.org/abs/2107.10064
Ao, X., Zhang, X., Yang, H., Yin, F., Liu, C.: Cross-modal prototype learning for zero-shot handwriting recognition. In: 2019 International Conference on Document Analysis and Recognition, ICDAR 2019, Sydney, Australia, September 20–25, 2019, pp. 589–594. IEEE (2019)
Cao, Z., Lu, J., Cui, S., Zhang, C.: Zero-shot handwritten Chinese character recognition with hierarchical decomposition embedding. Pattern Recognit. 107, 107488 (2020)
Huang, Y., Jin, L., Peng, D.: Zero-shot Chinese text recognition via matching class embedding. In: 16th International Conference on Document Analysis and Recognition, ICDAR 2021, Lausanne, Switzerland, September 5–10, 2021, Proceedings, Part III, ser. Lecture Notes in Computer Science, vol. 12823, pp. 127–141. Springer (2021)
Liu, C., Yang, C., Qin, H., Zhu, X., Liu, C., Yin, X.: Towards open-set text recognition via label-to-prototype learning. Pattern Recognit. 134, 109109 (2023)
Liu, C., Yang, C., Yin, X.: Open-set text recognition via character-context decoupling. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18–24, 2022, pp. 4513–4522. IEEE (2022)
Chen, J., Li, B., Xue, X.: Zero-shot Chinese character recognition with stroke-level decomposition. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19–27 August 2021, pp. 615–621 (2021). www.ijcai.org
Zhang, J., Matsumoto, T.: Improving character-level japanese-chinese neural machine translation with radicals as an additional input feature. In: 2017 International Conference on Asian Language Processing (IALP), pp. 172–175. IEEE (2017)
Lampert, C.H., Nickisch, H., Harmeling, S.: Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 453–465 (2014)
Wang, T., Xie, Z., Li, Z., Jin, L., Chen, X.: Radical aggregation network for few-shot offline handwritten Chinese character recognition. Pattern Recognit. Lett. 125, 821–827 (2019)
Wang, W., Zhang, J., Du, J., Wang, Z., Zhu, Y.: DenseRAN for offline handwritten Chinese character recognition. In: 16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, Niagara Falls, NY, USA, August 5–8, 2018, pp. 104–109. IEEE Computer Society (2018)
Zhang, J., Zhu, Y., Du, J., Dai, L.: Trajectory-based radical analysis network for online handwritten Chinese character recognition. In: 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, August 20–24, 2018, pp. 3681–3686. IEEE Computer Society (2018)
Zhang, J., Zhu, Y., Du, J., Dai, L.: Radical analysis network for zero-shot learning in printed Chinese character recognition. In: 2018 IEEE International Conference on Multimedia and Expo, ICME 2018, San Diego, CA, USA, July 23–27, 2018, pp. 1–6. IEEE Computer Society (2018)
Ke, Y., Hagiwara, M.: Cnn-encoded radical-level representation for Japanese processing. Trans. Japanese Soc. Artif. Intell. 33(4), D–I23 (2018)
Liu, Y., Liu, Q., Chen, J., Wang, Y.: Reading chinese in natural scenes with a bag-of-radicals prior. In: 33rd British Machine Vision Conference,: BMVC 2022, London, UK, November 21–24, 2022, p. 969. BMVA Press (2022)
Zu, X., Yu, H., Li, B., Xue, X.: Chinese character recognition with augmented character profile matching. In: MM ’22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10–14, 2022, pp. 6094–6102. ACM (2022)
Chen, Z., Yang, W., Li, X.: Stroke-based autoencoders: Self-supervised learners for efficient zero-shot Chinese character recognition (2022). [Online]. Available: http://arxiv.org/abs/2207.08191
Yu, H., Chen, J., Li, B., Xue, X.: Chinese character recognition with radical-structured stroke trees (2022). [Online]. Available: http://arxiv.org/abs/2211.13518
He, S., Schomaker, L.: Open set Chinese character recognition using multi-typed attributes (2018). [Online]. Available: http://arxiv.org/abs/1808.08993
Li, B., Tang, X., Qi, X., Chen, Y., Xiao, R.: Hamming OCR: A locality sensitive hashing neural network for scene text recognition (2020). [Online]. Available: https://arxiv.org/abs/2009.10874
Chen, J., Yu, H., Ma, J., Guan, M., Xu, X., Wang, X., Qu, S., Li, B., Xue, X.: Benchmarking Chinese text recognition: Datasets, baselines, and an empirical study (2021). [Online]. Available: https://arxiv.org/abs/2112.15093
Zhang, J., Du, J., Dai, L.: Radical analysis network for learning hierarchies of Chinese characters. Pattern Recognit. 103, 107305 (2020)
Zeng, J., Xu, R., Wu, Y., Li, H., Lu, J.: STAR: zero-shot chinese character recognition with stroke- and radical-level decompositions (2022). [Online]. Available: http://arxiv.org/abs/2210.08490
Diao, X., Shi, D., Tang, H., Wu, L., Li, Y., Xu, H.: REZCR: A zero-shot character recognition method via radical extraction (2022). [Online]. Available: https://arxiv.org/abs/2207.05842
Brunelli, R.: Template Matching Techniques in Computer Vision: Theory and Practice. John Wiley & Sons (2009)
Paz-Argaman, T., Tsarfaty, R., Chechik, G., Atzmon, Y.: ZEST: Zero-shot learning from text descriptions using textual similarity and visual summarization. In: Findings of the Association for Computational Linguistics: EMNLP. Association for Computational Linguistics 2020, 569–579 (2020)
Yang, C., Liu, C., Yin, X.: Weakly correlated knowledge integration for few-shot image classification. Int. J. Autom. Comput. 19(1), 24–37 (2022)
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5–10, 2016, pp. 3630–3638. Barcelona, Spain (2016)
Koch, G., Zemel, R., Salakhutdinov, R., et al.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol. 2, 1st edn. Lille (2015)
Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18–24 July 2021, Virtual Event, ser. Proceedings of Machine Learning Research, vol. 139, pp. 8748–8763. PMLR (2021)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171–4186. Association for Computational Linguistics (2019)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding with unsupervised learning (2018)
Ma, Z., Luo, G., Gao, J., Li, L., Chen, Y., Wang, S., Zhang, C., Hu, W.: Open-vocabulary one-stage detection with hierarchical visual-language knowledge distillation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18–24, 2022, pp. 14 054–14 063. IEEE (2022)
Huang, G., Luo, X., Wang, S., Gu, T., Su, K.: Hippocampus-heuristic character recognition network for zero-shot learning in Chinese character recognition. Pattern Recognit. 130, 108818 (2022)
Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513–523 (1988)
Tay, Y., Dehghani, M., Abnar, S., Shen, Y., Bahri, D., Pham, P., Rao, J., Yang, L., Ruder, S., Metzler, D.: Long range arena : A benchmark for efficient transformers. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3–7, 2021. OpenReview.net (2021)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Yin, XC., Yang, C., Liu, C. (2024). Open-Set Text Recognition Implementations(I): Label-to-Representation Mapping. In: Open-Set Text Recognition. SpringerBriefs in Computer Science. Springer, Singapore. https://doi.org/10.1007/978-981-97-0361-6_4
Download citation
DOI: https://doi.org/10.1007/978-981-97-0361-6_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0360-9
Online ISBN: 978-981-97-0361-6
eBook Packages: Computer ScienceComputer Science (R0)