Abstract
Deep networks are widely used in few-shot learning methods, but deep networks suffer from large-scale network parameters and computational effort. Aiming at the above problems, we present a novel few-shot learning method with deep balanced network and acceleration strategy. Firstly, a series of simple linear operations are applied to few original features to obtain the more features. More features are obtained with fewer parameters, thus reducing the network parameters and computational effort. Then the local cross-channel interaction mechanism without dimensionality reduction is used to further improve the performance with nearly no increase in parameters and computational effort, so as to obtain a deep balanced network to balance performance, parameters, and computational effort. Finally, an acceleration strategy is designed to solve the problem that the gradient update in the deep network takes a tremendous amount of time in new tasks, speeding up the adaptation process. The experimental results of traditional and fine-grained image classification show that the few-shot learning method with deep balanced network can achieve or even exceed the classification accuracy of some existing methods with fewer network parameters and computational effort. The cross-domain experiments further demonstrate the advantages of the method above the domain shift. Simultaneously, the time required for classification in new tasks can be significantly decreased by using the acceleration strategy.
Similar content being viewed by others
References
Bi Z, Yu L, Gao H et al (2020) Improved vgg model-based efficient traffic sign recognition for safe driving in 5G scenarios. Int J Mach Learn Cybern. https://doi.org/10.1007/s13042-020-01185-5
Chen B, Zhao T, Liu J et al (2021) Multipath feature recalibration densenet for image classification. Int J Mach Learn Cybern 12(3):651–660
Fourati H, Maaloul R, Chaari L (2021) A survey of 5G network systems: challenges and machine learning approaches. Int J Mach Learn Cybern 12(2):385–431
Mahindru A, Sangal AL (2021) Semidroid: a behavioral malware detector based on unsupervised machine learning techniques using feature selection approaches. Int J Mach Learn Cybern 12(5):1369–1411
Jiang H, Zhan J, Sun B et al (2020) An MADM approach to covering-based variable precision fuzzy rough sets: an application to medical diagnosis. Int J Mach Learn Cybern 11(9):2181–2207
Wang Y, Yao Q, Kwok J et al (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv 53(3):1–34
Hospedales T, Antoniou A, Micaelli P et al (2020) Meta-learning in neural networks: a survey. arXiv:2004.05439
Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the International Conference on Machine Learning (ICML), Sydney, AUSTRALIA, pp 1126–1135
Nichol A, Achiam J, Schulman J (2018) On first-order meta-learning algorithms. arXiv:1803.02999
Vinyals O, Blundell C, Lillicrap T et al (2016) Matching networks for one shot learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), Barcelona, SPAIN, pp 3630–3638
Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), Long Beach, CA, USA, pp 4077–4087
Sung F, Yang Y, Zhang L et al (2018) Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, pp 1199–1208
Ravi S, Larochelle H (2017) Optimization as a model for few-shot learning. In: Proceedings of the International Conference on Learning Representations (ICLR), Toulon, FRANCE, https://openreview.net/forum?id=rJY0-Kcll
Santoro A, Bartunov S, Botvinick M et al (2016) Meta-learning with memory-augmented neural networks. In: Proceedings of the International Conference on Machine Learning (ICML), New York City, NY, USA, pp 1842–1850
Mishra N, Rohaninejad M, Chen X et al (2017) A simple neural attentive meta-learner. arXiv:1707.03141
Munkhdalai T, Yu H (2017) Meta networks. In: Proceedings of the International Conference on Machine Learning (ICML), Sydney, AUSTRALIA, pp 2554–2563
Li Z, Zhou F, Chen F et al (2017) Meta-sgd: learning to learn quickly for few-shot learning. arXiv:1707.09835
Zhang R, Che T, Ghahramani Z et al (2018) Metagan: an adversarial approach to few-shot learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), Montréal, CANADA, pp 2371–2380
Munkhdalai T, Yuan X, Mehri S et al (2018) Rapid adaptation with conditionally shifted neurons. In: Proceedings of the International Conference on Machine Learning (ICML), Stockholm, SWEDEN, pp 3661–3670
Lee K, Maji S, Ravichandran A et al (2019) Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 10657–10665
Wang X, Bao A, Cheng Y et al (2019) Weight-sharing multi-stage multi-scale ensemble convolutional neural network. Int J Mach Learn Cybern 10(7):1631–1642
Sun Q, Liu Y , Chen Z et al (2019) Meta-transfer learning through hard tasks. arXiv:1910.03648
Han K, Wang Y, Tian Q et al (2020) Ghostnet: more features from cheap operations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ELECTR NETWORK, pp 1577–1586
Wang Q, Wu B, Zhu P et al (2020) Eca-net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), ELECTR NETWORK, pp 11531–11539
Raghu A, Raghu M, Bengio S et al (2019) Rapid learning or feature reuse? towards understanding the effectiveness of maml. arXiv:1909.09157
Bertinetto L, Henriques JF, Torr PHS et al (2018) Meta-learning with differentiable closed-form solvers. arXiv:1805.08136v3
Oreshkin BN, Rodriguez P, Lacoste A (2018) Tadam: task dependent adaptive metric for improved few-shot learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS), Montréal, CANADA, pp 721–731
Rusu AA, Rao D, Sygnowski J et al (2018) Meta-learning with latent embedding optimization. arXiv:1807.05960
Liu Y, Lee J, Park M et al (2018) Learning to propagate labels: transductive propagation network for few-shot learning. arXiv:1805.10002
Franceschi L, Frasconi P, Salzo S et al (2018) Bilevel programming for hyperparameter optimization and meta-learning. In: Proceedings of the International Conference on Machine Learning (ICML), Stockholm, SWEDEN, pp 1568–1577
Li W, Wang L, Xu J et al (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 7253–7260
Gidaris S, Komodakis N (2018) Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, pp 4367–4375
Chen W, Liu Y, Kira Z et al (2019) A closer look at few-shot classification. arXiv:1904.04232
Bauer M, Rojas-Carulla M, Świątkowski JB, et al (2017) Discriminative k-shot learning using probabilistic models. arXiv:1706.00326.
Li W, Wang L, Huo J et al (2020) Asymmetric distribution measure for few-shot learning. arXiv:2002.00153
Yu Z, Raschka S (2020) Looking back to lower-level information in few-shot learning. arXiv:2005.13638
Li S, Chen D, Liu B et al (2019) Memory-based neighbourhood embedding for visual recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Koera (South), pp 6101–6110
Ren M, Liao R, Fetaya E et al (2018) Incremental few-shot learning with attention attractor networks. arXiv:1810.07218v1
Qiao L, Shi Y, Li J et al (2019) Transductive episodic-wise adaptive metric for few-shot learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp 3602–3611.
Ravichandran A, Bhotika R, Soatto S (2019) Few-shot learning with embedded class models and shot-free meta training. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp 331–339
Lifchitz Y, Avrithis Y, Picard S et al (2019) Dense classification and implanting for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp 9250–9259
Dhillon GS, Chaudhari P, Ravichandran A et al (2019) A baseline for few-shot image classification. arXiv:1909.02729
Patacchiola M, Turner J, Crowley EJ et al (2019) Bayesian meta-learning for the few-shot setting via deep kernels. arXiv:1910.05199
Funding
This work was supported by the National Natural Science Foundation of China under Grant 61772532 and Grant 61976215.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, K., Wang, X., Zhang, T. et al. Few-shot learning with deep balanced network and acceleration strategy. Int. J. Mach. Learn. & Cyber. 13, 133–144 (2022). https://doi.org/10.1007/s13042-021-01373-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-021-01373-x