[1]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]
Copy

Multi-level decision optimization in relational networks for few-shot learning method

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 4 Page number: 882-893 Column: 学术论文—机器学习 Public date: 2025-08-05
Title:
Multi-level decision optimization in relational networks for few-shot learning method
Author(s):
MIAO Wanyu;  GOU Guanglei;  ZHONG Sheng;  BAI Ruifeng;  WEN Lang
College of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, China
Keywords:
few-shot learning; deep learning; decision theory; image classification; relation network; uncertainty analysis; feature extraction; rough set theory
CLC:
TP391
DOI:
10.11992/tis.202406016
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.
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.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems