Abstract
Few-shot learning (FSL) refers to adapt model to novel classes with few annotations. Existing methods generally utilize a single model’s information directly extracted from samples. Extra information are helpful to enhance the generation of the model. This paper focuses on designing a dual-model structure to learn the correlation between two models and introduce the center loss to cluster the same sort of samples and enhance the representation of samples. The center loss is to improve the generalization of the active branch. Moreover, we combine meta-learning. The meta-training has multiple tasks, and each task has two stages in our work, which firstly trains one model with soft labels from another fixed model and center loss. The optimal predictions of the active model are close to the soft and actual labels. Meanwhile, the same samples will gather together, attempting to minimize the intra-class differences. It could enhance the generalization and robustness of the model. We conduct experiments on miniImageNet, tieredImageNet and CUB. The results show the excellence of our proposed method.
Similar content being viewed by others
Data availability
All data generated or analyzed during this study are included in this paper. The data of this work is available on request from the authors. The data of MiniImageNet tieredImageNet, and CUB are also available in the public repository.
References
Bhatti UA, Yu Z, Hasnain A, Nawaz SA, Yuan L, Wen L, Bhatti MA (2022) Evaluating the impact of roads on the diversity pattern and density of trees to improve the conservation of species. Envi Sci Pollut Res 1–11
Bhatti UA, Yuan L, Yu Z, Nawaz SA, Mehmood A, Bhatti MA, Nizamani MM, Xiao S et al (2021) Predictive data modeling using sp-knn for risk factor evaluation in urban demographical healthcare data. J Med Imaging Health Inform 11(1):7–14
Bhatti UA, Yu Z, Li J, Nawaz SA, Mehmood A, Zhang K, Yuan L (2020) Hybrid watermarking algorithm using clifford algebra with arnold scrambling and chaotic encryption. IEEE Access 8:76386–76398
Bhatti UA, Yu Z, Yuan L, Nawaz SA, Aamir M, Bhatti MA (2022) A robust remote sensing image watermarking algorithm based on region-specific surf. In: Proceedings of International Conference on Information Technology and Applications: ICITA 2021, pp. 75–85. Springer
Bhatti UA, Yu Z, Yuan L, Zeeshan Z, Nawaz SA, Bhatti M, Mehmood A, Ain QU, Wen L (2020) Geometric algebra applications in geospatial artificial intelligence and remote sensing image processing. IEEE Access 8:155783–155796
Wu Y, Liu H, Fu Y (2017) Low-shot face recognition with hybrid classifiers. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops
Mahajan K, Sharma M, Vig L (2020) Metadermdiagnosis: Few-shot skin disease identification using meta-learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 730–731
Chen Y, Peng X, Kong L, Dong G, Remani A, Leach R (2021) Defect inspection technologies for additive manufacturing. Int J Extreme Manuf 3(2):022002. https://doi.org/10.1088/2631-7990/abe0d0
Chen C, Yang X, Xu C, Huang X, Ma Z (2021) Eckpn: Explicit class knowledge propagation network for transductive few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6596–6605
Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (Eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc., ???
Chen Y, Wang X, Liu Z, Xu H, Darrell T (2020) A new meta-baseline for few-shot learning
Weinberger KQ, Saul LK (2009) Distance metric learning for large margin nearest neighbor classification. J Mach Learn Res 10(2)
Bateni P, Goyal R, Masrani V, Wood F, Sigal L (2020) Improved few-shot visual classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14493–14502
Garcia V, Bruna J (2017) Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043
Liu G, Zhao L, Li W, Guo D, Fang X (2021) Class-wise metric scaling for improved few-shot classification. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 586–595
Finn C, Abbeel P, Levine S (2017) Modelagnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135. PMLR
Yan X, Ye Y, Qiu X, Manic M, Yu H (2019) Cmib: unsupervised image object categorization in multiple visual contexts. IEEE Trans Ind Inform 16(6):3974–3986
Yan X, Mao Y, Ye Y, Yu H, Wang F-Y (2022) Explanation guided cross-modal social image clustering. Inform Sci 593:1–16
Lin Y, Gou Y, Liu X, Bai J, Lv J, Peng X (2022) Dual contrastive prediction for incomplete multi-view representation learning. IEEE Trans Patterna Mach Intell
Buciluǎ C, Caruana R, Niculescu-Mizil A (2006) Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 535–541
Zhang Y, Xiang T, Hospedales TM, Lu H (2018) Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4320–4328
Yan X, Ye Y, Qiu X, Yu H (2020) Synergetic information bottleneck for joint multi-view and ensemble clustering. Inform Fus 56:15–27
Ravi S, Larochelle H (2016) Optimization as a model for few-shot learning
Nichol A, Achiam J, Schulman J (2018) On first-order meta-learning algorithms. arXivpreprint arXiv:1803.02999
Lee Y, Choi S (2018) Gradient-based metalearning with learned layerwise metric and subspace. In: International Conference on Machine Learning, pp. 2927–2936. PMLR
Grant E, Finn C, Levine S, Darrell T, Griffiths T (2018) Recasting gradient-based metalearning as hierarchical bayes. arXiv preprint arXiv:1801.08930
Zhang R, Che T, Ghahramani Z, Bengio Y, Song Y (2018) Metagan: An adversarial approach to few-shot learning. Adv Neur Inform Proc Syst 31
Rusu AA, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R (2018) Meta-learning with latent embedding optimization. arXiv preprint arXiv:1807.05960
Jiang X, Havaei M, Varno F, Chartrand G, Chapados N, Matwin S (2018) Learning to learn with conditional class dependencies. In: International Conference on Learning Representations
Widhianingsih TDA, Kang D-K (2021) Augmented domain agreement for adaptable meta-learner on few-shot classification. Appl Intell 1–17
Koch G, Zemel R, Salakhutdinov R et al (2015) Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol. 2, p. 0. Lille
Vinyals O, Blundell C, Lillicrap T, Wierstra D et al (2016) Matching networks for one shot learning. Adv Neur Inform Proc Syst 29
Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199–1208
Oreshkin B, Rodríguez López P, Lacoste A (2018) Tadam: Task dependent adaptive metric for improved few-shot learning. Adv Neur Inform Proc Syst 31
Li W, Xu J, Huo J, Wang L, Gao Y, Luo J (2019) Distribution consistency based covariance metric networks for few-shot learning. Proceedings of the AAAI Conference on Artificial Intelligence 33:8642–8649
Yoon SW, Seo J, Moon J (2019) Tapnet: Neural network augmented with task-adaptive projection for few-shot learning. In: International Conference on Machine Learning, pp. 7115–7123. PMLR
Requeima J, Gordon J, Bronskill J, Nowozin S, Turner RE (2019) Fast and flexible multi-task classification using conditional neural adaptive processes. Adv Neur Inform Proc Syst 32
Zhang C, Cai Y, Lin G, Shen C (2020) Deepemd: Few-shot image classification with differentiable earth mover’s distance and structured classifiers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12203–12213
Kim J, Kim T, Kim S, Yoo CD (2019) Edgelabeling graph neural network for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11–20
Liu Y, Lee J, Park M, Kim S, Yang E, Hwang SJ, Yang Y (2018) Learning to propagate labels: Transductive propagation network for few-shot learning. arXiv preprint arXiv:1805.10002
Yang L, Li L, Zhang Z, Zhou X, Zhou E, Liu Y (2020) Dpgn: Distribution propagation graph network for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13390–13399
Tang S, Chen D, Bai L, Liu K, Ge Y, Ouyang W (2021) Mutual crf-gnn for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2329–2339
Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y (2014) Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neur Inform Proc Syst 25
Guo Q, Wang X, Wu Y, Yu Z, Liang D, Hu X, Luo P (2020) Online knowledge distillation via collaborative learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Liu Y, Cao J, Li B, Yuan C, Hu W, Li Y, Duan Y (2019) Knowledge distillation via instance relationship graph. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Zhou B, Lapedriza A, Xiao J, Torralba A, Oliva A (2014) Learning deep features for scene recognition using places database. Adv Neur Inform Proc Syst 27
Park W, Kim W, You K, Cho M (2020) Diversified mutual learning for deep metric learning. In: European Conference on Computer Vision, pp. 709–725. Springer
Tian Y, Wang Y, Krishnan D, Tenenbaum JB, Isola P (2020) Rethinking few-shot image classification: A good embedding is all you need? In: European Conference on Computer Vision, pp. 266–282. Springer
Zhou Z, Qiu X, Xie J, Wu J, Zhang C (2021) Binocular mutual learning for improving few-shot classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 8402–8411
Wang X, Zhang R, Sun Y, Qi J (2018) Kdgan: Knowledge distillation with generative adversarial networks. Adv Neur Inform Proc Syst 31
Liu Y, Chen K, Liu C, Qin Z, Luo Z, Wang J (2019) Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2604–2613
Minoofam SAH, Bastanfard A, Keyvanpour MR (2021) Trcla: A transfer learning approach to reduce negative transfer for cellular learning automata. IEEE Trans Neur Netw Learn Sys
Gori M, Monfardini G, Scarselli F (2005) A new model for learning in graph domains. In: Proceedings. 2005 IEEE International Joint Conference on Neural Networks, vol. 2, pp. 729–734
Arandjelovic R, Gronat P, Torii A, Pajdla T, Sivic J (2016) Netvlad: Cnn architecture for weakly supervised place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5297–5307
Ma J, Xie H, Han G, Chang S-F, Galstyan A, Abd-Almageed W (2021) Partnerassisted learning for few-shot image classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10573–10582
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)
Kumar V, Glaude H, de Lichy C, Campbell W (2019) A closer look at feature space data augmentation for few-shot intent classification. arXiv preprint arXiv:1910.04176
Kang D, Kwon H, Min J, Cho M (2021) Relational embedding for few-shot classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8822–8833
Wertheimer D, Tang L, Hariharan B (2021) Few-shot classification with feature map reconstruction networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8012–8021
Xie J, Long F, Lv J, Wang Q, Li P (2022) Joint distribution matters: Deep brownian distance covariance for few-shot classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7972–7981
Tseng H-Y, Lee H-Y, Huang J-B, Yang M-H (2020) Cross-domain few-shot classification via learned feature-wise transformation. arXiv preprint arXiv:2001.08735
Wang Y, Chao W-L, Weinberger KQ, van der Maaten L (2019) Simpleshot: Revisiting nearest-neighbor classification for few-shot learning. arXiv preprint arXiv:1911.04623
Ziko I, Dolz J, Granger E, Ayed IB (2020) Laplacian regularized few-shot learning. In: International Conference on Machine Learning, pp. 11660–11670. PMLR
Hu SX, Moreno PG, Xiao Y, Shen X, Obozinski G, Lawrence ND, Damianou A (2020) Empirical bayes transductive metalearning with synthetic gradients. arXiv preprint arXiv:2004.12696
Zhao Y, Cheung N-M (2023) Fs-ban: Born-again networks for domain generalization few-shot classification. IEEE Trans Image Proc
Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum JB, Larochelle H, Zemel RS (2018) Meta-learning for semisupervised few-shot classification. arXiv preprint arXiv:1803.00676
Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset
Krause J, Stark M, Deng J, Fei-Fei L (2013) 3d object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554–561
Zhou B, Lapedriza A, Khosla A, Oliva A, Torralba A (2017) Places: A 10 million image database for scene recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1452–1464
Van Horn G, Mac Aodha O, Song Y, Cui Y, Sun C, Shepard A, Adam H, Perona P, Belongie S (2018) The inaturalist species classification and detection dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8769–8778
Das R, Wang Y-X, Moura JM (2021) On the importance of distractors for fewshot classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9030–9040
Yue Z, Zhang H, Sun Q, Hua X-S (2020) Interventional few-shot learning. Adv Neur Inform Proc Syst 33:2734–2746
Chen W-Y, Liu Y-C, Kira Z, Wang Y-CF, Huang J-B (2019) A closer look at few-shot classification. arXiv preprint arXiv:1904.04232
Acknowledgements
This work is supported by National Natural Science Foundation of China under grant 61771322, and the Fundamental Research Foundation of Shenzhen under Grant JCYJ20220531100814033.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xiong, M., Cao, W. & Zhao, Z. Dual-model Collaborative Learning with Knowledge Clustering for Few-shot Image Classification. Multimed Tools Appl 83, 26527–26546 (2024). https://doi.org/10.1007/s11042-023-16551-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16551-y