Abstract
Few-shot learning, which aims to identify new classes with very few samples, is an increasingly popular and crucial research topic in the machine learning. Many models use distance measurement to determine similarities among single samples and achieve accurate classification results. However, distance calculations incur substantial costs and time based on a single sample, and the linear measurement model cannot accurately represent the differences and connections between samples. This paper proposes a coarse-grained granulation relation network (CGRN) model for few-shot classification. First, all the single samples of each class are clustered into coarse grain to represent the feature information of all the class samples, which can significantly reduce computational complexities. Second, a relation network is built to measure the degree of similarity among the test samples and the coarse grain obtained above, which can reveal the differences and connections between the samples. The experimental results demonstrate that this model outperforms some popular distance measurement-based few-shot learning models. For example, CGRN is at least 0.5% better than other models in 20-way 5-shot on the Omniglot dataset and achieves 0.8% improvement over the second-best model in 5-way 1-shot on the tiered-ImageNet dataset.
Similar content being viewed by others
References
Balte A, Pise N, Kulkarni P (2014) Meta-learning with landmarking: A survey. International Journal of Computer Applications 975:8887
Dietterich TG (1997) Machine-learning research. AI Mag 18(4):97–97
Edwards H, Storkey A (2017) Towards a neural statistician. Stat Sci 1050:20
Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning, pp 1126–1135
Goodfellow I, Bengio Y, Courville A (2016) Machine learning basics. Deep Learn 1:98–164
Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 6(3):610–621
Kaiser Ł, Nachum O, Roy A, Bengio S (2017) Learning to remember rare events. arXiv:1703.03129
Khodizadeh-Nahari M, Ghadiri N, Baraani-Dastjerdi A, Sack JR (2021) A novel similarity measure for spatial entity resolution based on data granularity model: Managing inconsistencies in place descriptions. Appl Intell 51:6104–6123
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: International conference on learning representations
Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: International conference on machine learning
Lake B, Salakhutdinov R, Gross J, Tenenbaum J (2011) One shot learning of simple visual concepts. In: Annual meeting of the cognitive science society
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Lu D, Weng Q (2007) A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing 28(5):823–870
Min S, Lee B, Yoon S (2017) Deep learning in bioinformatics. Brief Bioinform 18(5):851–869
Munkhdalai T, Yu H (2017) Meta networks. In: International conference on machine learning, pp 2554–2563
Oh J, Yoo H, Kim C, Yun SY (2021) Boil: Towards representation change for few-shot learning. In: International conference on learning representations
Oreshkin BN, Rodriguez P, Lacoste A (2018) TADAM: Task Dependent adaptive metric for improved few-shot learning. In: International conference on neural information processing systems, pp 719–729
Peng Y, Flach PA, Soares C, Brazdil P (2002) Improved dataset characterisation for meta-learning. In: International conference on discovery science, Springer, pp 141–152
Ravi S, Larochelle H (2016) Optimization as a model for few-shot learning. In: International conference on learning representations
Ravichandran A, Bhotika R, Soatto S (2019) Few-shot learning with embedded class models and shot-free meta training. In: IEEE/CVF International conference on computer vision, pp 331–339
Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum JB, Larochelle H, Zemel RS (2018) Meta-learning for semi-supervised few-shot classification. In: International conference on learning representations
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252
Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) One-shot learning with memory-augmented neural networks. arXiv:1605.06065
Satorras VG, Estrach JB (2018) Few-shot learning with graph neural networks. In: International conference on learning representations
Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: International conference on neural information processing systems, pp 4080–4090
Snell J, Zemel R (2020) Bayesian few-shot classification with one-vs-each pólya-gamma augmented gaussian processes. In: International conference on learning representations
Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: Relation network for few-shot learning. In: IEEE Conference on computer vision and pattern recognition, pp 1199–1208
Vilalta R, Drissi Y (2002) A perspective view and survey of meta-learning. Artif Intell Rev 18(2):77–95
Vinyals O, Blundell C, Lillicrap T, Wierstra D et al (2016) Matching networks for one shot learning. In: International conference on neural information processing systems, pp 3630–3638
Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv 53(3):1–34
Wertheimer D, Hariharan B (2019) Few-shot learning with localization in realistic settings. In: IEEE/CVF Conference on computer vision and pattern recognition, pp 6558–6567
Xue Y, Deng Y (2021) Decision making under measure-based granular uncertainty with intuitionistic fuzzy sets. Appl Intell 51:6224–6233
Zhou A, Li Y (2021) Structural attention network for graph. Appl Intell 51:6255–6264
Zhou W, Liu C, Lei J, Yu L, Luo T (2021) HFNEt: Hierarchical feedback network with multilevel atrous spatial pyramid pooling for RGB-d saliency detection. Neurocomputing
Zhou W, Liu J, Lei J, Yu L, Hwang JN (2021) GMNEt: Graded-feature multilabel-learning network for RGB-thermal urban scene semantic segmentation. IEEE Trans Image Process 30:7790–7802
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant No. 62141602, and the Natural Science Foundation of Fujian Province under Grant Nos. 2021J011003 and 2021J011006.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jia, X., Su, Y. & Zhao, H. Few-shot learning via relation network based on coarse-grained granulation. Appl Intell 53, 996–1008 (2023). https://doi.org/10.1007/s10489-022-03332-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03332-7