Abstract
Ensembling is a very well-known strategy consisting in fusing several different models to achieve a new model for classification or regression tasks. Over the years, ensembling has been proven to provide superior performance in various contexts related to pattern recognition and artificial intelligence. Moreover, the basic ideas that are at the basis of ensembling have been a source of inspiration for the design of the most recent deep learning architectures. Indeed, a close analysis of those architectures shows that some connections among layers and groups of layers achieve effects similar to those obtainable by bagging, boosting and stacking, which are the well-known three basic approaches to ensembling. However, we argue that research has not fully leveraged the potential offered by ensembling. Indeed, this paper investigates some possible approaches to the combination of weak learners, or sub-components of weak learners, in the context of bagging. Based on previous results obtained in specific domains, we extend the approach to a reference dataset obtaining encouraging results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bojer, C.S., Meldgaard, J.P.: Kaggle forecasting competitions: An overlooked learning opportunity. Int. J. Forecast. 37(2), 587–603 (2021)
Boland, P.J.: Majority systems and the condorcet jury theorem. J. Royal Statist. Soc. Ser. D (The Statistician) 38(3), 181–189 (1989)
Bruno, A., Martinelli, M., Moroni, D.: Exploring ensembling in deep learning. Pattern Recognit Image Anal. 32(3), 519–521 (2022). https://doi.org/10.1134/S1054661822030087
Bruno, A., et al.: Improving plant disease classification by adaptive minimal ensembling. Front. Artifi. Intell. (2022). https://doi.org/10.3389/frai.2022.868926
Deng, J., Dong, W., Socher, R., Li, L., Kai Li, Li Fei-Fei: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009). https://doi.org/10.1109/CVPR.2009.5206848
Deng, L., Yu, D.: Deep convex net: A scalable architecture for speech pattern classification. In: Twelfth Annual Conference of the International Speech Communication Association (2011)
Dong, X., Yu, Z., Cao, W., Shi, Y., Ma, Q.: A survey on ensemble learning. Front. Comp. Sci. 14(2), 241–258 (2020)
Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3–7 May (2021)
Ganaie, M.A., Hu, M., et al.: Ensemble deep learning: A review. arXiv preprint arXiv:2104.02395 (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Krizhevsky, A., Nair, V., Hinton, G.: Cifar-10 (canadian institute for advanced research). http://www.cs.toronto.edu/kriz/cifar.html
Mohanty, S.P., Hughes, D.P., Salathé, M.: Using deep learning for image-based plant disease detection. Front. Plant Sci. 7, 1419 (2016)
Pouyanfar, S., et al.: A survey on deep learning: Algorithms, techniques, and applications. ACM Comput. Surv. (CSUR) 51(5), 1–36 (2018)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Schapire, R.E.: Explaining AdaBoost. In: Schölkopf, B., Luo, Z., Vovk, V. (eds.) Empirical Inference, pp. 37–52. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-41136-6_5
Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green AI. Commun. ACM 63(12), 54–63 (2020)
Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)
Veit, A., Wilber, M.J., Belongie, S.: Residual networks behave like ensembles of relatively shallow networks. In: Advances in Neural Information Processing Systems 29 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this paper
Cite this paper
Bruno, A., Moroni, D., Martinelli, M. (2023). Revisiting Ensembling for Improving the Performance of Deep Learning Models. In: Rousseau, JJ., Kapralos, B. (eds) Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges. ICPR 2022. Lecture Notes in Computer Science, vol 13644. Springer, Cham. https://doi.org/10.1007/978-3-031-37742-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-37742-6_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-37741-9
Online ISBN: 978-3-031-37742-6
eBook Packages: Computer ScienceComputer Science (R0)