基于模糊推理的模糊原型网络

doi:10.11772/j.issn.1001-9081.2020091482

摘要/Abstract

摘要： 针对真实数据具有的模糊性和不确定性会严重影响小样本学习分类结果这一问题，改进并优化了传统的小样本学习原型网络，提出了基于模糊推理的模糊原型网络（FPN）。首先，从卷积神经网络（CNN）和模糊神经网络两个方向分别获取图像特征信息；然后，对获得的两部分信息进行线性知识融合，得到最终的图像特征；最后，度量各个类别原型到查询集的欧氏距离，得到最终的分类效果。在小样本学习分类的主流数据集Omniglot和miniImageNet上进行一系列实验。实验结果显示：在miniImageNet数据集上，所提模型在5类1样本的实验设置下精度达到49.38%，在5类5样本的实验设置下精度达到67.84%，在30类1样本的实验设置下精度达到51.40%；在Omniglot数据集上该模型的精度相较于传统的原型网络同样有较大提升。

关键词: 小样本学习, 模糊推理, 原型网络, 特征融合, 深度学习

Abstract: In order to solve the problem that the fuzziness and uncertainty of real data may seriously affect the classification results of few-shot learning, a Fuzzy Prototype Network (FPN) based on fuzzy reasoning was proposed by improving and optimizing the traditional few-shot learning prototype network. Firstly, the image feature information was obtained from Convolutional Neural Network (CNN) and fuzzy neural network, respectively. Then, linear knowledge fusion was performed on the two obtained parts of information to obtain the final image features. Finally, to achieve the final classification effect, the Euclidean distance between each category prototype and the query set was measured. A series of experiments were carried out on the mainstream datasets Omniglot and miniImageNet for few-shot learning classification. On miniImageNet dataset, the model achieves accuracy of 49.38% under the experimental setting of 5-way 1-shot, accuracy of 67.84% under the experimental setting of 5-way 5-shot, and accuracy of 51.40% under the experimental setting of 30-way 1-shot; and compared with the traditional prototype network, the model also has the accuracy greatly improved on Omniglot dataset.

Key words: few-shot learning, fuzzy reasoning, prototype network, feature fusion, deep learning

中图分类号:

TP183

杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.

DU Yan, LYU Liangfu, JIAO Yichen. Fuzzy prototype network based on fuzzy reasoning[J]. Journal of Computer Applications, 2021, 41(7): 1885-1890.

参考文献

[1] ALFASSY A,KARLINSKY L,AIDES A,et al. LaSO:label-set operations networks for multi-label few-shot learning[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:6541-6550.
[2] ZHANG H, ZHANG J, KONIUSZ P. Few-shot learning via saliency-guided hallucination of samples[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:2765-2774.
[3] CHEN Z,FU Y,WANG Y X,et al. Image deformation metanetworks for one-shot learning[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:8672-8681.
[4] FINN C,ABBEEL P,LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proceedings of the 34th International Conference on Machine Learning. New York:JMLR. org,2017:1126-1135.
[5] VINYALS O,BLUNDELL C,LILLICRAP T,et al. Matching networks for one shot learning[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook,NY:Curran Associates Inc.,2016:3637-3645.
[6] SNELL J,SWERSKY K,ZEMEL R. Prototypical networks for fewshot learning[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook,NY:Curran Associates Inc.,2017:4080-4090.
[7] SCHWARTZ E,KARLINSKY L,FERIS R,et al. Baby steps towards few-shot learning with multiple semantics[EB/OL].[2020-08-20]. https://arxiv.org/pdf/1906.01905.pdf.
[8] GARCIA V, BRUNA J. Few-shot learning with graph neural networks[EB/OL].[2020-08-20]. https://arxiv.org/pdf/1711.04043.pdf.
[9] XING C,ROSTAMZADEH N,ORESHKIN B N,et al. Adaptive cross-modal few-shot learning[EB/OL].[2020-08-20]. https://arxiv.org/pdf/1902.07104.pdf.
[10] DENG Y,REN Z,KONG Y,et al. A hierarchical fused fuzzy deep neural network for data classification[J]. IEEE Transactions on Fuzzy Systems,2017,25(4):1006-1012.
[11] MUNKHDALAI T,YU H. Meta networks[C]//Proceedings of the 34th International Conference on Machine Learning. New York:JMLR. org,2017:2554-2563.
[12] JAMAL M A,QI G. Task agnostic meta-learning for few-shot learning[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:11711-11719.
[13] LI Z,ZHOU F,CHEN F,et al. Meta-SGD:learning to learn quickly for few-shot learning[EB/OL].[2020-08-20]. https://arxiv.org/pdf/1707.09835.pdf.
[14] YANG F,YANG Y,ZHANG L,et al. Learning to compare:relation network for few shot learning[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:1199-1208.
[15] LI W,XU J,HUO J,et al. Distribution consistency based covariance metric networks for few-shot learning[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto, CA:AAAI Press,2019:8642-8649.
[16] LAKE B M,SALAKHUTDINOV R,GROSS J,et al. One shot learning of simple visual concepts[J]. Proceedings of the Annual Meeting of the Cognitive Science Society,2011,33:2568-2573.
[17] ORESHKIN B N,RODRIGUEZ P,ALEXANDRE L. TADAM:task dependent adaptive metric for improved few-shot learning[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc.,2018:719-729.
[18] WANG X,YU F,WANG R,et al. TAFE-Net:task-aware feature embeddings for low shot learning[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:1831-1840.
[19] SANTORO A,BARTUNOV S,BOTVINICK M,et al. One-shot learning with memory-augmented neural networks[C]//Proceedings of the 33rd International Conference on Machine Learning. New York:JMLR. org,2016:1842-1850.
[20] TRIANTAFILLOU E,ZEMEL R,URTASUN R. Few-shot learning through an information retrieval lens[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc., 2017:2255-2265.
[21] GIDARIS S,KOMODAKIS N. Generating classification weights with GNN denoising autoencoders for few-shot learning[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:21-30.
[22] ZHANG H, ZHANG J, KONIUSZ P. Few-shot learning via saliency-guided hallucination of samples[EB/OL]. (2019-04-06)[2020-03-12]. http://arxiv.org/abs/1904.03472v1.
[23] BODYANSKIY Y,PELESHKO D,RASHKEVYCH Y,et al. The autoencoder based on generalized neo-fuzzy neuron and its fast learning for deep neural networks[C]//Proceedings of the IEEE 2nd International Conference on Data Stream Mining and Processing. Piscataway:IEEE,2018:113-118.
[24] HU Z,BODYANSKIY Y,TYSHCHENKO O K. A deep cascade neural network based on extended neo-fuzzy neurons and its adaptive learning algorithm[C]//Proceedings of the IEEE 1st Ukraine Conference on Electrical and Computer Engineering. Piscataway:IEEE,2017:801-805.
[25] ANGELOV P,GU X. A cascade of deep learning fuzzy rule-based image classifier and SVM[C]//Proceedings of the 2017 IEEE International Conference on Systems, Man, and Cybernetics. Piscataway:IEEE,2017:746-751.
[26] YEGANEJOU M, DICK S, MILLER J. Interpretable deep convolutional fuzzy classifier[J]. IEEE Transactions on Fuzzy Systems,2020,28(7):1407-1419
[27] XI Z, PANOUTSOS G. Interpretable machine learning:convolutional neural networks with RBF fuzzy logic classification rules[C]//Proceedings of the 2018 International Conference on Intelligent Systems. Piscataway:IEEE,2018:448-454.
[28] YEGANEJOU M,DICK S. Improved deep fuzzy clustering for accurate and interpretable classifiers[C]//Proceedings of the 2019 IEEE International Conference on Fuzzy Systems. Piscataway:IEEE,2019:1-7.
[29] ZADEH L A. Fuzzy sets[J]. Information and Control,1965,8(3):338-353.
[30] MARINOS P N. Fuzzy logic and its application to switching systems[J]. IEEE Transactions on Computers,1969,C-18(4):343-348.
[31] ZHANG H,LU J. Creating ensembles of classifiers via fuzzy clustering and deflection[J]. Fuzzy Sets and Systems,2010,161(13):1790-1802.
[32] YUAN W,CHAO L. Online evolving interval type-2 intuitionistic fuzzy LSTM-neural networks for regression problems[J]. IEEE Access,2019,7:35544-35555.
[33] KIM J,KIM T,KIM S,et al. Edge-labeling graph neural network for few-shot learning[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:11-20.
[34] CHEN W Y,LIU Y C,KIRA Z,et al. A closer look at few-shot classification[EB/OL].[2020-08-25]. https://arxiv.org/pdf/1904.04232.pdf.
[35] 吴正文. 卷积神经网络在图像分类中的应用研究[D]. 成都:电子科技大学, 2015:1-4. (WU Z W. Application of convolutional neural network in image classification[D]. Chengdu:University of Electronic Science and Technology of China,2015:1-4.)
[36] 鞠初旭. 模糊神经网络的研究及应用[D]. 成都:电子科技大学,2012:7-20. (JU C X. Research and application of fuzzy neural network[D]. Chengdu:University of Electronic Science and Technology of China,2012:7-20.)
[37] SCHÖNFELD E,EBRAHIMI S,SINHA S,et al. Generalized zero- and few-shot learning via aligned variational autoencoders[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:8239-8247.
[38] ZHOU J,CUI G,HU S,et al. Graph neural networks:a review of methods and applications[J]. AI Open,2020,1:57-81.
[39] KOSKO B. Fuzzy systems as universal approximators[J]. IEEE Transactions on Computers,1994,43(11):1329-1333.