Abstract
Recent few-shot learning methods mostly only use a single classifier to complete image classification. In general, a single classifier is likely to be overfitting because of its inherent drawbacks. However, the recognition rate of categorization will be significantly increased if we can utilize the complementary information of different classifiers. For the few-shot problem, the test samples come from new classes, which makes it difficult for a single classifier to distinguish, and it can be improved via decision fusion. In this paper, we propose decision fusion for few-shot learning (DF-FSL) to overcome the drawbacks of single classifier. To be specific, we assign the task to two classifiers, which are the logical regression classifier and probabilistic collaborative representation-based classifier (ProCRC), then allow the two classifiers to learn together through several iterations. Finally, we evaluate our approach on four benchmark image datasets, which include CIFAR-FS, CUB, miniImageNet and tieredImageNet datasets, and two remote sensing image datasets which are RSD46-WHU and NWPU-RESIS45. The experimental results illustrate the complementarity between different classifiers and show that the performance of our proposed DF-FSL method provides an obvious improvement. And DF-FSL can make great progress in few-shot remote sensing image classification.





Similar content being viewed by others
References
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
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
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Lake BM, Salakhutdinov RR, Tenenbaum J (2013) One-shot learning by inverting a compositional causal process. Adv Neural Inf Process Syst 26:2526–2534
Li Y, Yang J (2020) Few-shot cotton pest recognition and terminal realization. Comput Electron Agric 169:105240
Li Y, Chao X (2021) Semi-supervised few-shot learning approach for plant diseases recognition. Plant Methods 17:1–10
Xing E, Jordan M, Russell SJ, Ng A (2002) Distance metric learning with application to clustering with side-information. Adv Neural Inf Process Syst 15:521–528
Mishra A (2019) Dhfml: deep heterogeneous feature metric learning for matching photograph and cartoon pairs. Int J Multimed Inf Retr 8(3):135–142
Hao F, Cheng J, Wang L, Cao J (2019) Instance-level embedding adaptation for few-shot learning. IEEE Access 7:100501–100511
Andrychowicz M, Denil M, Gomez S, Hoffman MW, Pfau D, Schaul T, Shillingford B, De Freitas N (2016) Learning to learn by gradient descent by gradient descent. Adv Neural Inf Process Syst 29:3981–3989
Li Y, Yang J (2021) Meta-learning baselines and database for few-shot classification in agriculture. Comput Electron Agric 182:106055
Revaud J, Weinzaepfel P, De Souza C, Pion N, Csurka G, Cabon Y, Humenberger M (2019) R2d2: repeatable and reliable detector and descriptor. arXiv:1906.06195
Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 30:4077–4087
Bertinetto L, Henriques JF, Torr PH, Vedaldi A (2018) Meta-learning with differentiable closed-form solvers. arXiv:1805.08136
Xing L, Shao S, Liu W, Han A, Pan X, Liu B-D (2022) Learning task-specific discriminative embeddings for few-shot image classification. Neurocomputing 488:1–13
Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv (CSUR) 53(3):1–34
Xu R, Xing L, Shao S, Liu B, Zhang K, Liu W (2022) Co-learning for few-shot learning. Neural Process Lett 54(4):3339–3356
Yang J, Jiang J, Guo Y (2022) MHA-WoML: multi-head attention and Wasserstein-OT for few-shot learning. Int J Multimed Inf Ret 11(4):681–694
Salakhutdinov R, Tenenbaum J, Torralba A (2012) One-shot learning with a hierarchical nonparametric Bayesian model. In: Proceedings of ICML workshop on unsupervised and transfer learning. JMLR Workshop and Conference Proceedings, pp 195–206
Rezende D, Danihelka I, Gregor K, Wierstra D, et al (2016) One-shot generalization in deep generative models. In: International conference on machine learning, pp 1521–1529. PMLR
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. PMLR
Graves A, Wayne G, Danihelka I (2014) Neural turing machines. arXiv:1410.5401
Ravi S, Larochelle H (2016) Optimization as a model for few-shot learning
Hao F, He F, Cheng J, Wang L, Cao J, Tao D (2019) Collect and select: semantic alignment metric learning for few-shot learning. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 8460–8469
Lee K, Maji S, Ravichandran A, Soatto S (2019) Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10657–10665
Hao F, He F, Cheng J, Tao D (2021) Global-local interplay in semantic alignment for few-shot learning. IEEE Trans Circuits Syst Video Technol 32(7):4351–4363
Kuncheva LI, Bezdek JC, Duin RP (2001) Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recognit 34(2):299–314
Cruz RM, Sabourin R, Cavalcanti GD (2018) Dynamic classifier selection: recent advances and perspectives. Inf Fusion 41:195–216
Kuncheva LI (2002) A theoretical study on six classifier fusion strategies. IEEE Trans Pattern Anal Mach Intell 24(2):281–286
Sagi O, Rokach L (2018) Ensemble learning: a survey. Wiley Interdiscip Rev Data Min Knowl Discov 8(4):1249
Gong Y, Mao L, Li C (2021) Few-shot learning for named entity recognition based on BERT and two-level model fusion. Data Intell 3(4):568–577
Cai S, Zhang L, Zuo W, Feng X (2016) A probabilistic collaborative representation based approach for pattern classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2950–2959
Lan R, Zhou Y (2017) An extended probabilistic collaborative representation based classifier for image classification. In: 2017 IEEE international conference on multimedia and expo (ICME), pp 1392–1397. IEEE
King G, Zeng L (2001) Logistic regression in rare events data. Political Anal 9(2):137–163
Peng C-YJ, Lee KL, Ingersoll GM (2002) An introduction to logistic regression analysis and reporting. J Edu Res 96(1):3–14
Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset
Vinyals O, Blundell C, Lillicrap T, Wierstra D et al (2016) Matching networks for one shot learning. Adv Neural Inf Process Syst 29:3630–3638
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. arXiv:1803.00676
Krizhevsky A, Hinton G, et al (2009) Learning multiple layers of features from tiny images
Cheng G, Han J, Lu X (2017) Remote sensing image scene classification: benchmark and state of the art. Proc IEEE 105(10):1865–1883
Long Y, Gong Y, Xiao Z, Liu Q (2017) Accurate object localization in remote sensing images based on convolutional neural networks. IEEE Trans Geosci Remote Sens 55(5):2486–2498
Wang Y, Xu C, Liu C, Zhang L, Fu Y (2020) Instance credibility inference for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12836–12845
Xing L, Zhao L, Cao W, Ge X, Liu W, Liu B (2022) Class shared dictionary learning for few-shot remote sensing scene classification. IEEE Geosci Remote Sens Lett 19:1–5
Rodríguez P, Laradji I, Drouin A, Lacoste A (2020) Embedding propagation: smoother manifold for few-shot classification. Springer, Berlin, pp 121–138
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
Kim J, Kim H, Kim G (2020) Model-agnostic boundary-adversarial sampling for test-time generalization in few-shot learning. Springer, Berlin, pp 599–617
Qiao L, Shi Y, Li J, Wang Y, Huang T, Tian Y (2019) Transductive episodic-wise adaptive metric for few-shot learning. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 3603–3612
Chikontwe P, Kim S, Park SH (2022) Cad: Co-adapting discriminative features for improved few-shot classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 14554–14563
Mangla P, Kumari N, Sinha A, Singh M, Krishnamurthy B, Balasubramanian VN (2020) Charting the right manifold: Manifold mixup for few-shot learning, pp 2218–2227
Dhillon GS, Chaudhari P, Ravichandran A, Soatto S (2019) A baseline for few-shot image classification. arXiv:1909.02729
Fei N, Lu Z, Xiang T, Huang S (2020) Melr: meta-learning via modeling episode-level relationships for few-shot learning
Yoon SW, Seo J, Moon J (2019) Tapnet: neural network augmented with task-adaptive projection for few-shot learning, pp 7115–7123. PMLR
Xing C, Rostamzadeh N, Oreshkin B, Pinheiro PO (2019) Adaptive cross-modal few-shot learning. Adv Neural Information Process Syst 32:4847–4857
Xu C, Fu Y, Liu C, Wang C, Li J, Huang F, Zhang L, Xue X (2021) Learning dynamic alignment via meta-filter for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5182–5191
Oh J, Yoo H, Kim C, Yun S-Y (2020) Boil: towards representation change for few-shot learning. arXiv:2008.08882
Afrasiyabi A, Lalonde J-F, Gagné C (2021) Mixture-based feature space learning for few-shot image classification, pp 9041–9051
Tian Y, Wang Y, Krishnan D, Tenenbaum JB, Isola P (2020) Rethinking few-shot image classification: a good embedding is all you need? Springer, Berlin, pp 266–282
Chen W-Y, Liu Y-C, Kira Z, Wang Y-CF, Huang J-B (2019) A closer look at few-shot classification. arXiv:1904.04232
Yu Z, Chen L, Cheng Z, Luo J (2020) Transmatch: a transfer-learning scheme for semi-supervised few-shot learning, pp 12856–12864
Oreshkin B, Rodríguez López P, Lacoste A (2018) Tadam: task dependent adaptive metric for improved few-shot learning. Adv Neural Inf Process Syst 31:719–729
Zhang P, Bai Y, Wang D, Bai B, Li Y (2021) Few-shot classification of aerial scene images via meta-learning. Remote Sens 13(1):108
Simon C, Koniusz P, Nock R, Harandi M (2020) Adaptive subspaces for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4136–4145
Acknowledgements
The paper was supported by the Natural Science Foundation of Shandong Province, China (Grant No. ZR2019MF073), the Fundamental Research Funds for the Central Universities, China University of Petroleum (East China) (Grant No. 20CX05001A), the Major Scientific and Technological Projects of CNPC (No. ZD2019-183-008).
Author information
Authors and Affiliations
Contributions
TY, WL, and BL contributed to the conception of the study, TY and BL performed the experiment; TY, WL, and BL contributed significantly to the analysis and manuscript preparation; TY and BL performed the data analyses and wrote the manuscript; WL and BL helped perform the analysis with constructive discussions. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
There are no declared competing interests of the authors that are pertinent to the subject matter of this study.
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
Yuan, T., Liu, W., Yan, F. et al. Decision fusion for few-shot image classification. Int J Multimed Info Retr 12, 31 (2023). https://doi.org/10.1007/s13735-023-00281-w
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13735-023-00281-w