[1]缪宛谕,苟光磊,钟声,等.多级决策优化关系网络的小样本学习方法[J].智能系统学报,2025,20(4):882-893.[doi:10.11992/tis.202406016]
MIAO Wanyu,GOU Guanglei,ZHONG Sheng,et al.Multi-level decision optimization in relational networks for few-shot learning method[J].CAAI Transactions on Intelligent Systems,2025,20(4):882-893.[doi:10.11992/tis.202406016]
点击复制
MIAO Wanyu,GOU Guanglei,ZHONG Sheng,et al.Multi-level decision optimization in relational networks for few-shot learning method[J].CAAI Transactions on Intelligent Systems,2025,20(4):882-893.[doi:10.11992/tis.202406016]
多级决策优化关系网络的小样本学习方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第4期
页码:
882-893
栏目:
学术论文—机器学习
出版日期:
2025-08-05
- Title:
- Multi-level decision optimization in relational networks for few-shot learning method
- Keywords:
- few-shot learning; deep learning; decision theory; image classification; relation network; uncertainty analysis; feature extraction; rough set theory
- 分类号:
- TP391
- 文献标志码:
- 2025-2-21
- 摘要:
- 针对小样本学习中数据稀缺性的问题以及传统二支决策方法仅提供接受或拒绝两种选择的局限性，本研究提出一种多级决策优化的小样本学习方法。提出多粒度特征提取模块对样本进行处理，构建具有不同粒度的特征层来获取不同感受野的语义信息，从而实现精确决策；提出多分支自适应特征细化模块来提升局部与全局的关键区域特征表示；通过关系网络计算获取各个尺度参数，构建恰当的相似度度量矩阵，并将其输入到提出的多级决策优化模块中，使得模型能够根据不同粒度层的特征自适应地调整决策中的不确定区域。通过在MiniImageNet和TieredImageNet两个公开数据集上进行实验验证，分类准确率均有一定提升，实验结果验证了本方法的有效性。
- Abstract:
- Addressing the issues of data scarcity in few-shot learning and the limitations of traditional binary decision methods that only offer accept or reject options, this study proposes a multi-level decision optimization approach for few-shot learning. Initially, a multi-granularity feature extraction module processes samples and constructs feature layers of different granularities to capture semantic information from various receptive fields, so as to make decisions precisely. Subsequently, a multi-branch adaptive feature refinement module is introduced to enhance the representation of key features in both local and global regions. By computing the parameters at various scales through relational networks, we construct an appropriate similarity matrix and input it into the proposed multi-level decision optimization module. This enables the model to adaptively adjust the uncertain regions in decision making based on features at different granularity levels. Finally, experimental validation on the MiniImageNet and TieredImageNet public datasets shows a significant improvement in classification accuracy, confirming effectiveness of this method.
- 参考文献/References:
-
[1] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.
[2] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[3] HINTON G, DENG Li, YU Dong, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE signal processing magazine, 2012, 29(6): 82-97.
[4] TAYE M M. Understanding of machine learning with deep learning: architectures, workflow, applications and future directions[J]. Computers, 2023, 12(5): 91.
[5] LI Feifei, FERGUS R, PERONA P. One-shot learning of object categories[J]. IEEE transactions on pattern analysis and machine intelligence, 2006, 28(4): 594-611.
[6] QI Guojun, LUO Jiebo. Small data challenges in big data era: a survey of recent progress on unsupervised and semi-supervised methods[J]. IEEE transactions on pattern analysis and machine intelligence, 2022, 44(4): 2168-2187.
[7] SNELL J, SWERSKY K, ZEMEL R S. Prototypical networks for few-shot learning[EB/OL]. (2017-03-15)[2024-06-11]. https://arxiv.org/abs/1703.05175v2.
[8] HUANG Huaxing, ZHANG Junjie, ZHANG Jian, et al. PTN: A poisson transfer network for semi-supervised few-shot learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021: 1602-1609.
[9] HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2261-2269.
[10] SUNG F, YANG Yongxin, ZHANG Li, et al. Learning to compare: relation network for few-shot learning[EB/OL]. (2017-11-16)[20224-06-11]. https://arxiv.org/abs/1711.06025v2.
[11] ZHENG Wenfeng, TIAN Xia, YANG Bo, et al. A few shot classification methods based on multiscale relational networks[J]. Applied sciences, 2022, 12(8): 4059.
[12] 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.
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.
[13] 姚一豫, 祁建军, 魏玲. 基于三支决策的形式概念分析、粗糙集与粒计算[J]. 西北大学学报(自然科学版), 2018, 48(4): 477-487.
YAO Yiyu, QI Jianjun, WEI Ling. Formal concept analysis, rough set analysis and granular computing based on three-way decisions[J]. Journal of Northwest University (natural science edition), 2018, 48(4): 477-487.
[14] QIAN Yuhua, ZHANG Hu, SANG Yanli, et al. Multigranulation decision-theoretic rough sets[J]. International journal of approximate reasoning, 2014, 55(1): 225-237.
[15] SONG Yisheng, WANG Ting, CAI Puyu, et al. A comprehensive survey of few-shot learning: evolution, applications, challenges, and opportunities[J]. ACM computing surveys, 2023, 55(13s): 1-40.
[16] 许栋, 杨关, 刘小明, 等. 基于自适应特征融合与转换的小样本图像分类[J]. 计算机工程与应用, 2022, 58(24): 223-232.
XU Dong, YANG Guan, LIU Xiaoming, et al. Few-shot learning image classification based on adaptive feature fusion and transformation[J]. Computer engineering and applications, 2022, 58(24): 223-232.
[17] WANG Yikai, XU Chengming, LIU Chen, et al. Instance credibility inference for few-shot learning[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 01285.
[18] MEHROTRA A, DUKKIPATI A. Generative adversarial residual pairwise networks for one shot learning[J]. (2017-03-23)[2024-06-11]. https://arxiv.org/abs/1703.08033.
[19] NAVEED H, ANWAR S, HAYAT M, et al. Survey: Image mixing and deleting for data augmentation[J]. Engineering applications of artificial intelligence, 2024, 131: 107791.
[20] 马岽奡, 唐娉, 赵理君, 等. 深度学习图像数据增广方法研究综述[J]. 中国图象图形学报, 2021, 26(3): 487-502.
MA Dongao, TANG Ping, ZHAO Lijun, et al. Review of data augmentation for image in deep learning[J]. Journal of image and graphics, 2021, 26(3): 487-502.
[21] VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning[EB/OL]. (2016-13)[2024-06-11]. https://arxiv.org/abs/1606.04080v2.
[22] LI Wenbin, WANG Lei, XU Jinglin, et al. Revisiting local descriptor based image-to-class measure for few-shot learning[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 00743.
[23] 周阳阳, 钱文彬, 王映龙, 等. 面向混合数据的代价敏感三支决策边界域分类方法[J]. 智能系统学报, 2022, 17(2): 411-419.
ZHOU Yangyang, QIAN Wenbin, WANG Yinglong, et al. Classification method of cost-sensitive three-way decision boundary region for hybrid data[J]. CAAI transactions on intelligent systems, 2022, 17(2): 411-419.
[24] 刘盾, 李天瑞, 杨新, 等. 三支决策-基于粗糙集与粒计算研究视角[J]. 智能系统学报, 2019, 14(6): 1111-1120.
LIU Dun, LI Tianrui, YANG Xin, et al. Three-way decisions: research perspectives for rough sets and granular computing[J]. CAAI transactions on intelligent systems, 2019, 14(6): 1111-1120.
[25] ATANASSOV K T. Intuitionistic fuzzy sets: theory and applications[M]. Heidelberg: Springer Nature, 1999.
[26] PEDRYCZ W. Shadowed sets: representing and processing fuzzy sets[J]. IEEE transactions on systems, man, and cybernetics Part B, Cybernetics, 1998, 28(1): 103-109.
[27] 苗夺谦, 张清华, 钱宇华, 等. 从人类智能到机器实现模型: 粒计算理论与方法[J]. 智能系统学报, 2016, 11(6): 743-757.
MIAO Duoqian, ZHANG Qinghua, QIAN Yuhua, et al. From human intelligence to machine implementation model: theories and applications based on granular computing[J]. CAAI transactions on intelligent systems, 2016, 11(6): 743-757.
[28] GUO Doudou, JIANG Chunmao, WU Peng. Three-way decision based on confidence level change in rough set[J]. International journal of approximate reasoning, 2022, 143: 57-77.
[29] YANG Dandan, DENG Tingquan, FUJITA H. Partial-overall dominance three-way decision models in interval-valued decision systems[J]. International journal of approximate reasoning, 2020, 126: 308-325.
[30] WANG Tianxing, LI Huaxiong, QIAN Yuhua, et al. A regret-based three-way decision model under interval type-2 fuzzy environment[J]. IEEE transactions on fuzzy systems, 2022, 30(1): 175-189.
[31] SAVCHENKO A V. Fast inference in convolutional neural networks based on sequential three-way decisions[J]. Information sciences, 2021, 560: 370-385.
[32] LI Huaxiong, ZHANG Libo, HUANG Bing, et al. Sequential three-way decision and granulation for cost-sensitive face recognition[J]. Knowledge-based systems, 2016, 91: 241-251.
[33] LI Zhaowen, ZHANG Pengfei, XIE Ningxin, et al. A novel three-way decision method in a hybrid information system with images and its application in medical diagnosis[J]. Engineering applications of artificial intelligence, 2020, 92: 103651.
[34] 张楠, 姜丽丽, 岳晓冬, 等. 效用三支决策模型[J]. 智能系统学报, 2016, 11(4): 459-468.
ZHANG Nan, JIANG Lili, YUE Xiaodong, et al. Utility-based three-way decisions model[J]. CAAI transactions on intelligent systems, 2016, 11(4): 459-468.
[35] SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 7298594.
[36] HU Jie, SHEN Li, ALBANIE S, et al. Squeeze-and-excitation networks[EB/OL]. (2017-09-05)[2024-04-10]. https://arxiv. org/abs/1709.01507v4.
[37] LIU Yanbin, LEE J, PARK M, et al. Learning to propagate labels: transductive propagation network for few-shot learning[EB/OL]. (2018-05-25)[2024-06-11]. https://arxiv.org/abs/1805.10002v5.
[38] CHEN Da, CHEN Yuefeng, LI Yuhong, et al. Self-supervised learning for few-shot image classification[C]//2021 IEEE International Conference on Acoustics, Speech and Signal Processing. Toronto: IEEE, 2021: 1745-1749.
[39] 陈龙, 张建林, 彭昊, 等. 多尺度注意力与领域自适应的小样本图像识别[J]. 光电工程, 2023, 50(4): 66-80.
CHEN Long, ZHANG Jianlin, PENG Hao, et al. Few-shot image classification via multi-scale attention and domain adaptation[J]. Opto-electronic engineering, 2023, 50(4): 66-80.
[40] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[EB/OL]. (2017-03-09)[2024-06-11]. https://arxiv.org/abs/1703.03400v3.
[41] YU Zhongjie, RASCHKA S. Looking back to lower-level information in few-shot learning[J]. Information, 2020, 11(7): 345.
[42] 汪航, 田晟兆, 唐青, 等. 基于多尺度标签传播的小样本图像分类[J]. 计算机研究与发展, 2022, 59(7): 1486-1495.
WANG Hang, TIAN Shengzhao, TANG Qing, et al. Few-shot image classification based on multi-scale label propagation[J]. Journal of computer research and development, 2022, 59(7): 1486-1495.
[43] GAO Farong, LUO Xingsheng, YANG Zhangyi, et al. Label smoothing and task-adaptive loss function based on prototype network for few-shot learning[J]. Neural networks, 2022, 156: 39-48.
[44] JIA Xiao, SU Yuling, ZHAO Hong. Few-shot learning via relation network based on coarse-grained granulation[J]. Applied intelligence, 2023, 53(1): 996-1008.
[45] 吕佳, 曾梦瑶, 董保森. 双路径合作的原型矫正小样本分类模型[J]. 计算机科学与探索, 2024, 18(3): 693-706.
LYU Jia, ZENG Mengyao, DONG Baosen. Prototype rectification few-shot classification model with dual-path cooperation[J]. Journal of frontiers of computer science and technology, 2024, 18(3): 693-706.
- 相似文献/References:
-
[1]张媛媛,霍静,杨婉琪,等.深度信念网络的二代身份证异构人脸核实算法[J].智能系统学报,2015,10(2):193.[doi:10.3969/j.issn.1673-4785.201405060]
ZHANG Yuanyuan,HUO Jing,YANG Wanqi,et al.A deep belief network-based heterogeneous face verification method for the second-generation identity card[J].CAAI Transactions on Intelligent Systems,2015,10():193.[doi:10.3969/j.issn.1673-4785.201405060]
[2]丁科,谭营.GPU通用计算及其在计算智能领域的应用[J].智能系统学报,2015,10(1):1.[doi:10.3969/j.issn.1673-4785.201403072]
DING Ke,TAN Ying.A review on general purpose computing on GPUs and its applications in computational intelligence[J].CAAI Transactions on Intelligent Systems,2015,10():1.[doi:10.3969/j.issn.1673-4785.201403072]
[3]马晓,张番栋,封举富.基于深度学习特征的稀疏表示的人脸识别方法[J].智能系统学报,2016,11(3):279.[doi:10.11992/tis.201603026]
MA Xiao,ZHANG Fandong,FENG Jufu.Sparse representation via deep learning features based face recognition method[J].CAAI Transactions on Intelligent Systems,2016,11():279.[doi:10.11992/tis.201603026]
[4]刘帅师,程曦,郭文燕,等.深度学习方法研究新进展[J].智能系统学报,2016,11(5):567.[doi:10.11992/tis.201511028]
LIU Shuaishi,CHENG Xi,GUO Wenyan,et al.Progress report on new research in deep learning[J].CAAI Transactions on Intelligent Systems,2016,11():567.[doi:10.11992/tis.201511028]
[5]马世龙,乌尼日其其格,李小平.大数据与深度学习综述[J].智能系统学报,2016,11(6):728.[doi:10.11992/tis.201611021]
MA Shilong,WUNIRI Qiqige,LI Xiaoping.Deep learning with big data: state of the art and development[J].CAAI Transactions on Intelligent Systems,2016,11():728.[doi:10.11992/tis.201611021]
[6]王亚杰,邱虹坤,吴燕燕,等.计算机博弈的研究与发展[J].智能系统学报,2016,11(6):788.[doi:10.11992/tis.201609006]
WANG Yajie,QIU Hongkun,WU Yanyan,et al.Research and development of computer games[J].CAAI Transactions on Intelligent Systems,2016,11():788.[doi:10.11992/tis.201609006]
[7]黄心汉.A3I:21世纪科技之光[J].智能系统学报,2016,11(6):835.[doi:10.11992/tis.201605022]
HUANG Xinhan.A3I: the star of science and technology for the 21st century[J].CAAI Transactions on Intelligent Systems,2016,11():835.[doi:10.11992/tis.201605022]
[8]宋婉茹,赵晴晴,陈昌红,等.行人重识别研究综述[J].智能系统学报,2017,12(6):770.[doi:10.11992/tis.201706084]
SONG Wanru,ZHAO Qingqing,CHEN Changhong,et al.Survey on pedestrian re-identification research[J].CAAI Transactions on Intelligent Systems,2017,12():770.[doi:10.11992/tis.201706084]
[9]杨梦铎,栾咏红,刘文军,等.基于自编码器的特征迁移算法[J].智能系统学报,2017,12(6):894.[doi:10.11992/tis.201706037]
YANG Mengduo,LUAN Yonghong,LIU Wenjun,et al.Feature transfer algorithm based on an auto-encoder[J].CAAI Transactions on Intelligent Systems,2017,12():894.[doi:10.11992/tis.201706037]
[10]王科俊,赵彦东,邢向磊.深度学习在无人驾驶汽车领域应用的研究进展[J].智能系统学报,2018,13(1):55.[doi:10.11992/tis.201609029]
WANG Kejun,ZHAO Yandong,XING Xianglei.Deep learning in driverless vehicles[J].CAAI Transactions on Intelligent Systems,2018,13():55.[doi:10.11992/tis.201609029]
[11]马岭,鲁越,蒋慧琴,等.基于小样本学习的LCD产品缺陷自动检测方法[J].智能系统学报,2020,15(3):560.[doi:10.11992/tis.201904020]
MA Ling,LU Yue,JIANG Huiqin,et al.An automatic small sample learning-based detection method for LCD product defects[J].CAAI Transactions on Intelligent Systems,2020,15():560.[doi:10.11992/tis.201904020]
[12]周凯锐,刘鑫,景丽萍,等.概念驱动的小样本判别特征学习方法[J].智能系统学报,2023,18(1):162.[doi:10.11992/tis.202203061]
ZHOU Kairui,LIU Xin,JING Liping,et al.Concept-driven discriminative feature learning for few-shot learning[J].CAAI Transactions on Intelligent Systems,2023,18():162.[doi:10.11992/tis.202203061]
[13]李小菲,苟光磊,韩岩奇,等.多尺度知识引导局部增强的小样本细粒度图像分类方法[J].智能系统学报,2024,19(5):1157.[doi:10.11992/tis.202309003]
LI Xiaofei,GOU Guanglei,HAN Yanqi,et al.Multiscale knowledge-guided local enhancement method for few-shot fine-grained image classification[J].CAAI Transactions on Intelligent Systems,2024,19():1157.[doi:10.11992/tis.202309003]
备注/Memo
收稿日期:2024-6-11。
基金项目:国家自然科学基金项目(62141201)；重庆市教委科学技术研究项目(KJZD-M202201102).
作者简介:缪宛谕，硕士研究生，主要研究方向为小样本学习、三支决策。E-mail：mwyy1007@163.com。;苟光磊，讲师，博士，主要研究方向为粗糙集理论和人工智能。主持重庆市科委基础科学与前沿技术研究项目、重庆市教委科学技术研究项目等科研项目 5 项，获发明专利授权3 项，发表学术论文 20 余篇，出版专著 1 部、教材 2 部。 E-mail：ggl@cqut.edu.cn。;钟声，硕士研究生，主要研究方向为三支决策、目标检测。E-mail：ferry@stu.cqut.edu.cn。
通讯作者:苟光磊. E-mail：ggl@cqut.edu.cn
更新日期/Last Update:
1900-01-01