Abstract
Few-shot learning aims to learn a classifier that has good generalization performance in new classes, where each class only a small number of labeled examples are available. The existing few-shot classification methods use the single-scale image do not learn effective feature representation. Moreover, most of previous methods still depend on standard metrics to calculate visual similarities, such as Euclidean or cosine distance. Standard metrics are independent of data and lack nonlinear internal structure that captures the similarity between data. In this paper, we propose a new method for few-shot learning problem, which learns a multi-scale feature space, and classification is performed by computing similarities between the multi-scale representation of the image and the label feature of each class (i.e. class representation). Our method, called the Multi-Scale Feature Network (MSFN), is trained end-to-end from scratch. The proposed method improves 1-shot accuracy from 50.44% to 54.48% and 5-shot accuracy from 68.2% to 69.06% on MiniImagenet dataset compared to competing approaches. Experimental results on Omniglot, MiniImagenet, Cifar100, CUB200, and Caltech256 datasets demonstrate the effectiveness of the proposed method.
Similar content being viewed by others
References
Boney R, Ilin A (2017) Semi-supervised few-shot learning with prototypical networks. arXiv preprint arXiv:1711.10856
Chen Z, Fu Y, Zhang Y, Jiang YG, Xue X, Sigal L (2018) Semantic feature augmentation in few-shot learning. arXiv preprint arXiv:1804.05298
Dixit M, Kwitt R, Niethammer M, Vasconcelos N (2017) Aga: Attribute-guided augmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7455-7463
Edwards H, Storkey A (2017) Towards a neural Statistician. arXiv preprint arXiv:1606.02185
Feifei L, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Transact Pattern Analysis Mach Intell (TPAMI) 28(4):594–611
Finn C, Abbeel P, Levine S (2017) Model-agnostic Meta-learning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp 1126-1135. JMLR.org
Ge W, Yu Y (2017). Borrowing treasures from the wealthy: Deep transfer learning through selective joint fine-tuning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1086-1095
Girshick R (2015) Fast R-CNN. In Proceedings of the IEEE international conference on computer vision, pp 1440–1448
Hariharan B, Girshick R (2017) Low-shot visual recognition by shrinking and hallucinating features.In Proceedings of the IEEE International Conference on Computer Vision, pp 3018–3027.
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.
Hilliard N, Hodas NO, Corley CD (2017) Dynamic input structure and network assembly for few-shot learning. arXiv preprint arXiv:1708.06819
Hilliard N, Phillips L, Howland S, Yankov A, Corley CD, Hodas NO (2018) Few-shot learning with metric-agnostic conditional embeddings. arXiv preprint arXiv:1802.04376
Huang G, Liu Z, Van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2261-2269
Kaiser L, Nachum O, Roy A, Bengio S (2017) Learning to remember rare events. In International Conference on Learning Representations (ICLR)
Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980
Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In ICML deep learning workshop (Vol. 2)
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems, pp 1097-1105
Li Z, Zhou F, Chen F, Li H (2017) Meta-SGD: Learning to learn quickly for few-shot learning. arXiv preprint arXiv:1707.09835
Mehrotra A, Dukkipati A (2017) Generative adversarial residual pairwise networks for one shot learning. arXiv preprint arXiv:1703.08033
Mishra N, Rohaninejad M, Chen X, Abbeel P (2018) A simple neural attentive meta-learner. arXiv preprint arXiv:1707.03141
Munkhdalai T, Yu H (2017) Meta networks. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp 2554-2563. JMLR. org
Ravi S, Larochelle H (2017) Optimization as a model for few-shot learning. In: International Conference on Learning Representations (ICLR)
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pp 91-99
Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum J, Larochelle H, Zemel RS (2018) Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676
Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:1605.06065
Garcia V, Bruna J (2017) Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043.
Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems, pp 4077-4087
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
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich, A (2015) Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9
Thrun S (1996) Learning to learn: introduction. Kluwer Academic Publishers, Dordrecht
Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. In Advances in neural information processing systems, pp 3630-3638
Wang P, Liu L, Shen C, Huang Z, van den Hengel A, Tao Shen H (2017) Multi-attention network for one shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2721-2729
Wang Y, Girshick R, Hebert M, Hariharan B (2018) Low-shot learning from imaginary data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7278-7286
Ye M, Guo Y (2018) Deep triplet ranking networks for one-shot recognition. arXiv preprint arXiv:1804.07275
Zhou F, Wu B, Li Z (2018) Deep Meta-learning: learning to learn in the concept space. arXiv preprint arXiv:1802.03596.
Funding
This study was funded by the National Natural Science Foundation of China under (grant number 61672202).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The whole authors are fulltime teachers of Hefei University of Technology besides the first author Mengya Han, and she is the fulltime student of Hefei University of Technology. The whole authors declare that we have no conflicts of interest to this work.
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
Han, M., Wang, R., Yang, J. et al. Multi-scale feature network for few-shot learning. Multimed Tools Appl 79, 11617–11637 (2020). https://doi.org/10.1007/s11042-019-08413-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08413-3