面向长尾分布甲骨文识别的自适应难度感知解耦学习方法

孙君为; 关素妍; 陈信宇; 王堃; 蔡院强

doi:10.11999/JEIT260327

面向长尾分布甲骨文识别的自适应难度感知解耦学习方法

doi: 10.11999/JEIT260327 cstr: 32379.14.JEIT260327

北京邮电大学计算机学院(国家示范性软件学院) 北京 100876

基金项目: 国家自然科学基金(62272058)

详细信息

作者简介:
孙君为：男，本科生，研究方向为甲骨文识别与破译、模式识别

关素妍：女，本科生，研究方向为甲骨文识别与破译

陈信宇：男，本科生，研究方向为甲骨文识别与破译

王堃：男，本科生，研究方向为甲骨文识别与破译

蔡院强：男，讲师，研究方向为计算文字学

通讯作者:
蔡院强，　caiyuanqiang@bupt.edu.cn

中图分类号: TP391.41; TP391.43; TP181
计量
- 文章访问数: 20
- HTML全文浏览量: 8
- PDF下载量: 1
- 被引次数: 0
出版历程
- 收稿日期: 2026-03-23
- 修回日期: 2026-06-28
- 录用日期: 2026-06-29
- 网络出版日期: 2026-07-12

Decoupled Learning for Long-tailed Oracle Bone Character Recognition Based on Adaptive Difficulty Sampling

School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing, 100876, China

Funds: The National Natural Science Foundation of China (No. 62272058)

摘要

摘要: 针对甲骨文识别场景中普遍存在的类别长尾分布问题，以及现有方法难以兼顾头部类别判别力与尾部稀缺样本识别性能的技术瓶颈，该文提出一种两阶段解耦学习方法。第一阶段结合混合数据增强与标签分布感知间隔损失，学习全局泛化的特征空间并构建鲁棒决策边界；第二阶段冻结骨干网络，提出基于类别识别难度的自适应采样策略，结合类别加权损失优化分类器，通过动态分配采样权重聚焦尾部与困难类别，实现头部与尾部类别识别性能的协同提升。在OBC306公开数据集上的实验结果表明，该文方法总体识别准确率达94.34%，平均识别准确率达89.89%，综合性能优于主流方法，可为低资源古文字识别提供技术支撑。
- 甲骨文识别 /
- 长尾分布 /
- 自适应难度采样 /
- 解耦学习
Abstract: Objective Oracle Bone Character (OBC) recognition is severely hindered by extreme long-tailed distributions and large intra-class variances. Conventional deep learning methods are easily dominated by head classes, whereas existing methods often over-fit tail classes or ignore intrinsic learning difficulties. To address these bottlenecks, a two-stage decoupled learning framework is proposed to improve the recognition of tail and difficult classes while preserving discriminative power for head classes. Methods The framework separates representation learning from classifier optimization. In the first stage, the backbone is trained using mixed augmentation (CutMix and RandAug) and label-distribution-aware margin (LDAM) loss to extract robust features and mitigate intra-class variance. In the second stage, the backbone is frozen. The classifier is optimized utilizing a novel class-difficulty-based adaptive sampling strategy, which dynamically allocates sampling weights based on historical training loss, coupled with a class-balanced loss (CBL) to refine decision boundaries. Results and Discussions Experiments on the highly imbalanced OBC306 dataset demonstrate that the proposed method achieves an overall accuracy of 94.34% and an average class accuracy of 89.89%. It significantly outperforms the Inception-v4 baseline by 19.61% in average class accuracy. Comprehensive ablation studies validatethat the difficulty sampling strategy successfully boosts the recognition of rare and challenging characters. Additionally, sensitivity and qualitative analyses further confirm the robustness and interpretability of the model. Conclusions The proposed decoupled learning algorithm effectively addresses long-tailed OBC recognition by balancing learning priorities across diverse classes. Mixed augmentation enriches sample diversity, while difficulty-aware sampling refines decision boundaries for complex tail characters without sacrificing head class performance. This framework provides a highly robust and scalable solution for the digital recognition of ancient scripts and archaeological AI applications.
- Oracle Bone Character recognition /
- Long-tailed distribution /
- Adaptive difficulty sampling /
- Decoupled learning

HTML全文

图 1 甲骨文由甲骨文骨片经多种算法技术数字化为图片形式样本

下载: 全尺寸图片幻灯片

图 2 OBC306数据集的真实分布图

下载: 全尺寸图片幻灯片

图 3 整体方法框架图

注：虚线表示在二阶段训练中，冻结骨干网络参数，只训练分类器，并且只在二阶段训练中启用难度采样器。

下载: 全尺寸图片幻灯片

图 4 训练实际情况分析

下载: 全尺寸图片幻灯片

图 5 在OBC306数据集上模型识别错误的样本，共分为四种错误类型

下载: 全尺寸图片幻灯片

图 6 OBC306测试集上200个识别错误的样本，共分为四种错误类别

下载: 全尺寸图片幻灯片

表 1 在OBC306数据集上，本文方法与其他甲骨文识别方法的对比分析

方法	识别类数	平均识别准确率(%)	总识别准确率(%)
Inception-v4^[4]	306	70.28	×
Mix-up^[7]	277	80.16	91.74
AGTGAN^[8]	306	85.36	×
CycleGAN^[20]	306	83.44	92.02
Decoupled-LTR^[10]	277	85.01	92.40
ADA-LTR^[21]	277	86.54	93.86
Diff-Oracle^[9]	275	88.07	94.12
本文方法	277	89.89	94.34

下载: 导出CSV

表 2 基于OBC306数据集的消融研究

CutMix	RandAug	DS	准确率(%)
CutMix	RandAug	DS	总识别准确率	平均识别准确率
×	×	×	92.23	78.11
√	×	×	94.40	81.85
×	√	×	92.86	79.64
√	√	×	94.71	83.87
×	×	√	93.01	80.57
×	√	√	94.60	82.21
√	√	√	94.48	89.47

下载: 导出CSV

表 3 基于Oracle-AYNU数据集的消融研究

CutMix	RandAug	DS	准确率(%)
CutMix	RandAug	DS	总识别准确率	平均识别准确率
×	×	×	77.32	65.14
√	×	×	78.11	65.35
×	√	×	75.32	63.29
√	√	×	76.89	64.06
×	×	√	82.37	79.75
×	√	√	79.55	73.42
√	√	√	80.56	75.48

下载: 导出CSV

表 4 比较不同$ {\alpha }_{c} $参数的性能

$ {\alpha }_{c} $参数	准确率(%)
$ {\alpha }_{c} $参数	总识别准确率	平均识别准确率
[0.1,0.1,0.1]	93.43	86.47
[0.5,0.5,0.5]	94.12	88.12
[0.9,0.9,0.9]	93.67	87.08
[0.1,0.5,0.9]	93.42	86.78
[0.9,0.5,0.1]	94.34	89.89

下载: 导出CSV

表 5 比较不同β参数的性能

β参数	准确率(%)
β参数	总识别准确率	平均识别准确率
0	94.96	86.02
0.9	94.90	87.00
0.99	94.80	88.03
0.999	94.48	89.47
0.9999	94.01	89.10

下载: 导出CSV

表 6 比较不同缩放因子s的性能

缩放因子s	准确率(%)
缩放因子s	总识别准确率	平均识别准确率
5	94.48	89.47
10	94.60	88.79
20	94.81	88.77
30	94.17	89.11

下载: 导出CSV

表 7 比较不同类别间隔最大值的性能

类别间隔最大值	准确率(%)
类别间隔最大值	总识别准确率	平均识别准确率
0.1	94.48	89.47
0.2	94.66	89.71
0.3	94.63	89.67
0.4	94.80	89.40
0.5	94.34	89.89

下载: 导出CSV

参考文献(25)

[1]	葛亮. 一百二十年来甲骨文材料的初步统计[J]. 汉字汉语研究, 2019(4): 33–54,125. doi: 10.13513/j.cnki.41-1041/h.2019.04.006. GE Liang. Preliminary statistics of inscribed oracle bones excavated in the past 120 years[J]. The Study of Chinese Characters and Language, 2019(4): 33–54,125. doi: 10.13513/j.cnki.41-1041/h.2019.04.006.
[2]	GUO Jun, WANG Changhu, ROMAN-RANGEL E, et al. Building hierarchical representations for oracle character and sketch recognition[J]. IEEE Transactions on Image Processing, 2016, 25(1): 104–118. doi: 10.1109/TIP.2015.2500019.
[3]	ZHANG Yikang, ZHANG Heng, LIU Yongge, et al. Oracle character recognition by nearest neighbor classification with deep metric learning[C]. Proceedings of 2019 International Conference on Document Analysis and Recognition, Sydney, Australia, 2019: 309–314. doi: 10.1109/ICDAR.2019.00057.
[4]	HUANG Shuangping, WANG Haobin, LIU Yongge, et al. OBC306: A large-scale oracle bone character recognition dataset[C]. Proceedings of International Conference on Document Analysis and Recognition, Sydney, Australia, 2019: 681–688. doi: 10.1109/ICDAR.2019.00114.
[5]	GUAN Haisu, WAN Jinpeng, LIU Yuliang, et al. An open dataset for the evolution of oracle bone characters: EVOBC[J]. arXiv preprint arXiv: 2401.12467, 2024. (查阅网上资料, 不确定文献类型及格式是否正确, 请确认).
[6]	韩佳艺, 刘建伟, 陈德华, 等. 深度长尾学习研究综述[J]. 自动化学报, 2025, 51(5): 985–1020. doi: 10.16383/j.aas.c240077. HAN Jiayi, LIU Jianwei, CHEN Dehua, et al. Survey on deep long-tailed learning[J]. Acta Automatica Sinica, 2025, 51(5): 985–1020. doi: 10.16383/j.aas.c240077.
[7]	LI Jing, WANG Qiufeng, ZHANG Rui, et al. Mix-up augmentation for oracle character recognition with imbalanced data distribution[C]. Proceedings of the 16th International Conference on Document Analysis and Recognition, Lausanne, Switzerland, 2021: 237–251. doi: 10.1007/978-3-030-86549-8_16.
[8]	HUANG Hongxiang, YANG Daihui, DAI Gang, et al. AGTGAN: Unpaired image translation for photographic ancient character generation[C]. Proceedings of the 30th ACM International Conference on Multimedia, Lisboa, Portugal, 2022: 5456–5467. doi: 10.1145/3503161.3548338.
[9]	LI Jing, WANG Qiufeng, WANG Siyuan, et al. Diff-Oracle: Deciphering oracle bone scripts with controllable diffusion model[J]. arXiv preprint arXiv: 2312.13631, 2024. (查阅网上资料, 不确定文献类型及格式是否正确, 请确认).
[10]	LI Jing, DONG Bin, WANG Qiufeng, et al. Decoupled learning for long-tailed oracle character recognition[C]. Proceedings of the 17th International Conference on Document Analysis and Recognition, San José, USA, 2023: 165–181. doi: 10.1007/978-3-031-41685-9_11.
[11]	YUN S, HAN D, CHUN S, et al. CutMix: Regularization strategy to train strong classifiers with localizable features[C]. Proceedings of International Conference on Computer Vision, Seoul, South Korea, 2019: 6022–6031. doi: 10.1109/ICCV.2019.00612.
[12]	CUBUK E D, ZOPH B, SHLENS J, et al. Randaugment: Practical automated data augmentation with a reduced search space[C]. Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, USA, 2020: 3008–3017. doi: 10.1109/CVPRW50498.2020.00359.
[13]	LI Jing, CHI Xueke, WANG Qiufeng, et al. A comprehensive survey of oracle character recognition: Challenges, datasets, methodology, and beyond[J]. Pattern Recognition, 2026, 169: 111824. doi: 10.1016/j.patcog.2025.111824.
[14]	ZHOU Xinlun, HUA Xingcheng, and LI Feng. A method of Jia Gu Wen recognition based on a two-level classification[C]. Proceedings of 3rd International Conference on Document Analysis and Recognition, Montreal, Canada, 1995: 833–836. doi: 10.1109/ICDAR.1995.602030.
[15]	栗青生, 杨玉星, 王爱民. 甲骨文识别的图同构方法[J]. 计算机工程与应用, 2011, 47(8): 112–114. doi: 10.3778/j.issn.1002-8331.2011.08.033. LI Qingsheng, YANG Yuxing, and WANG Aimin. Recognition of inscriptions on bones or tortoise shells based on graph isomorphism[J]. Computer Engineering and Applications, 2011, 47(8): 112–114. doi: 10.3778/j.issn.1002-8331.2011.08.033.
[16]	SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning[C]. Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, USA, 2017: 4278–4284. doi: 10.1609/aaai.v31i1.11231.
[17]	MAI C, PENAVA P, and BUETTNER R. Oracle bone inscription character recognition based on a novel convolutional neural network architecture[J]. IEEE Access, 2024, 12: 197021–197034. doi: 10.1109/ACCESS.2024.3521319.
[18]	毕晓君, 毛亚菲. 基于监督对比学习的小样本甲骨文字识别[J]. 智能系统学报, 2024, 19(1): 106–113. doi: 10.11992/tis.202309008. BI Xiaojun and 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.
[19]	刘宗昊, 彭文杰, 代港, 等. 语义增强的零样本甲骨文字符识别[J]. 电子学报, 2024, 52(10): 3347–3358. doi: 10.12263/DZXB.20240286. LIU Zonghao, PENG Wenjie, DAI Gang, et al. Semantic-enhanced zero-shot oracle character recognition[J]. Acta Electronica Sinica, 2024, 52(10): 3347–3358. doi: 10.12263/DZXB.20240286.
[20]	WANG Wei, ZHANG Ting, ZHAO Yiwen, et al. Improving oracle bone characters recognition via a CycleGAN-based data augmentation method[C]. Proceedings of the 29th International Conference on Neural Information Processing, Changsha, China, 2022: 88–100. doi: 10.1007/978-981-99-1645-0_8. (查阅网上资料,未找到本条文献出版地信息,请确认).
[21]	LI Jing, WANG Qiufeng, HUANG Kaizhu, et al. Towards better long-tailed oracle character recognition with adversarial data augmentation[J]. Pattern Recognition, 2023, 140: 109534. doi: 10.1016/j.patcog.2023.109534.
[22]	CAO Kaidi, WEI C, GAIDON A, et al. Learning imbalanced datasets with label-distribution-aware margin loss[C]. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, 2019: 140.
[23]	YU Sihao, GUO Jiafeng, ZHANG Ruqing, et al. A re-balancing strategy for class-imbalanced classification based on instance difficulty[C]. Proceedings of Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 70–79. doi: 10.1109/CVPR52688.2022.00017.
[24]	CUI Yin, JIA Menglin, LIN T Y, et al. Class-balanced loss based on effective number of samples[C]. Proceedings of Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 9260–9269. doi: 10.1109/CVPR.2019.00949.
[25]	YU Weihao, ZHOU Pan, YAN Shuicheng, et al. InceptionNeXt: When inception meets ConvNeXt[C]. Proceedings of Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2024: 5672–5683. doi: 10.1109/CVPR52733.2024.00542.