[1]BI Xiaojun,MAO Yafei.Few-shot oracle bone character recognition based on supervised contrastive learning[J].CAAI Transactions on Intelligent Systems,2024,19(1):106-113.[doi:10.11992/tis.202309008]
Copy

Few-shot oracle bone character recognition based on supervised contrastive learning

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 19 Number of periods: 2024 1 Page number: 106-113 Column: 学术论文—机器感知与模式识别 Public date: 2024-01-05
Title:
Few-shot oracle bone character recognition based on supervised contrastive learning
Author(s):
BI Xiaojun1; 2;  MAO Yafei3
1. Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Beijing 100081, China;
2. Department of Information Engineering, Minzu University of China, Beijing 100081, China;
3. College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
Keywords:
oracle bone character recognition; few-shot; supervised contrastive learning; EASY framework; deep learning; feature space; joint contrastive loss
CLC:
TP391
DOI:
10.11992/tis.202309008
Abstract:
Due to low frequency of occurrence of some characters in Oracle, directly using the deep neural network for recognition will produce serious overfitting, which will lead to poor recognition accuracy. To this end, this paper proposes a few-shot oracle bone character recognition method based on supervised contrastive learning. The ensemble augmented-shot Y-shaped (EASY) learning framework is selected as the backbone part of the network. Through training techniques such as collective data enhancement, multi-backbone network integration, and feature vector projection, etc., it is possible to directly use a small number of labeled samples for identification. And then, introducing the supervised contrastive learning and the concept of a joint contrastive loss to make the intra-class feature vectors in the feature space closer and the inter-class feature vectors further apart, thereby the model performance is improved further. The experimental results show that compared with the current best-performing Orc-Bert model, the accuracy of the few-shot oracle recognition model proposed in this paper has increased by 26.42% in the 1-shot task, 28.55% in the 3-shot task, and 23.98% in the 5-shot task, which better solves the problem of poor recognition accuracy of low-frequency oracle bone characters.
References:
[1] 谢乃和. 从殷墟走向世界的“绝学”甲骨文字研究: 韩国釜山“纪念甲骨文发现120周年国际学术研讨会”述评[J]. 管子学刊, 2020(3): 125–128
XIE Naihe. Flourishing from Yin Ruins to the world—a review of “busan, South Korea international symposium commemorating the 120th anniversary of oracle bone inscription discovery”[J]. Guan zi journal, 2020(3): 125–128
[2] GUPTA J, PATHAK S, KUMAR G. Deep learning (CNN) and transfer learning: a review[J]. Journal of physics:conference series, 2022, 2273(1): 012029.
[3] HUANG Shuangping, WANG Haobin, LIU Yongge, et al. OBC306: a large-scale oracle bone character recognition dataset[C]//2019 International Conference on Document Analysis and Recognition. Piscataway IEEE, 2020: 681?688.
[4] 安胜彪, 郭昱岐, 白宇, 等. 小样本图像分类研究综述[J]. 计算机科学与探索, 2023, 17(3): 511–532
AN Shengbiao, GUO Yuqi, BAI Yu, et al. Survey of few-shot image classification research[J]. Journal of frontiers of computer science and technology, 2023, 17(3): 511–532
[5] LI Na, HAO Huizhen, GU Qing, et al. A transfer learning method for automatic identification of sandstone microscopic images[J]. Computers & geosciences, 2017, 103: 111–121.
[6] LIU Wenhe, CHANG Xiaojun, YAN Yan, et al. Few-shot text and image classification via analogical transfer learning[J]. ACM transactions on intelligent systems and technology, 9(6): 71.
[7] LONG M, ZHU H, WANG J, JORDAN MI. Deep transfer learning with joint adaptation networks[C]//International Conference on Machine Learning. PMLR, 2017: 2208?2217.
[8] LONG Mingsheng, WANG Jianmin, JORDAN M I. Unsupervised domain adaptation with residual transfer networks[EB/OL]. (2017?02?16)[2023?09?06]. https://arxiv.org/abs/1602.04433.pdf.
[9] GE Weifeng, YU Yizhou. Borrowing treasures from the wealthy: deep transfer learning through selective joint fine-tuning[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 10?19.
[10] XIE Jiangtao, LONG Fei, LV Jiaming, et al. Joint distribution matters: deep Brownian distance covariance for few-shot classification[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 7962?7971.
[11] HAN Wenhui, REN Xinlin, LIN Hangyu, et al. Self-supervised learning of orc-bert augmentor for recognizing few-shot oracle characters[C]//Ishikawa H, Liu CL, Pajdla T, et al. Asian Conference on Computer Vision. Cham: Springer, 2021: 652?668.
[12] BENDOU Y, HU Yuqing, LAFARGUE R, et al. EASY: ensemble augmented-shot Y-shaped learning: state-of-the-art few-shot classification with simple ingredients[EB/OL]. (2022?02?07)[2023?09?06]. https://arxiv.org/abs/2201.09699.pdf
[13] MANGLA P, SINGH M, SINHA A, et al. Charting the right manifold: manifold mixup for few-shot learning[C]//2020 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2020: 2207?2216.
[14] ZHANG Chi, CAI Yujun, LIN Guosheng, et al. DeepEMD: few-shot image classification with differentiable earth mover’s distance and structured classifiers[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 12200?12210.
[15] LIU Jialin, CHAO Fei, LIN C M. Task augmentation by rotating for meta-learning[EB/OL]. (2020?02?08)[2023?09?06]. https://arxiv.org/abs/2003.00804.pdf.
[16] WANG Yan, CHAO Weilun, WEINBERGER K Q, et al. SimpleShot: revisiting nearest-neighbor classification for few-shot learning[EB/OL]. (2019?11?16)[2023?09?06]. https://arxiv.org/abs/1911.04623.pdf.
[17] KHOSLA P, TETERWAK P, WANG C. Supervised contrastive learning[J]. Advances in neural information processing systems, 2020, 33: 18661–18673.
[18] ZHANG Hongyi, CISSE M, DAUPHIN Y N, et al. Mixup: beyond empirical risk minimization[EB/OL]. (2017?10?25)[2023?09?06]. https://arxiv.org/abs/1710.09412.pdf.
[19] LOSHCHILOV I, HUTTER F. SGDR: stochastic gradient descent with warm restarts[EB/OL]. (2016?08?13)[2023?09?06]. https://arxiv.org/abs/1608.03983.pdf.
[20] MAI Zheda, LI Ruiwen, KIM H, et al. Supervised contrastive replay: revisiting the nearest class mean classifier in online class-incremental continual learning[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2021: 3589?3599.
[21] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2016: 770?778.
[22] WU Zhirong, XIONG Yuanjun, YU S X, et al. Unsupervised feature learning via non-parametric instance discrimination[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 3733?3742.
[23] VAN DEN OORD A, LI Yazhe, VINYALS O. Representation learning with contrastive predictive coding[EB/OL]. (2018?07?10)[2023?09?06]. https://arxiv.org/abs/1807.03748.pdf.
[24] TIAN Yonglong, KRISHNAN D, ISOLA P. Contrastive multiview coding[EB/OL].(2019?01?13)[2023?09?06]. https://arxiv.org/abs/1906.05849.pdf.
[25] LI Bang, DAI Qianwen, GAO Feng, et al. HWOBC-a handwriting oracle bone character recognition database[J]. Journal of physics:conference series, 2020, 1651(1): 012050.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems