Abstract
Few-shot learning is one of the most challenging problems in computer vision due to the difficulty of sample collection in many real-world applications. It aims at classifying a sample when the number of training samples for each identity is limited. Most of the existing few-shot learning models learn a distance metric with pairwise or triplet constraints. In this paper, we make initial attempts on learning local and global similarities simultaneously to improve the few-shot classification performance in terms of accuracy. In particular, our system differs in two aspects. Firstly, we develop a neural network to learn the pairwise local relationship between each pair of samples in the union set that is composed of support set and query set, which fully utilize the supervision. Secondly, we design a global similarity function from the manifold perspective. The latent assumption is that if the neighbors of one sample are similar to those of another sample, the global similarity between them will be high. Otherwise, the global similarity of the two samples will become very low even if the local similarity between them is high. Meanwhile, we propose a new loss according to the pairwise local loss and task-specific global loss, encouraging the model toward better generalization. Extensive experiments on three popular benchmarks (Omniglot, miniImageNet and tieredImageNet) demonstrate that our simple, yet effective approach can achieve competitive accuracy compared to the state-of-the-art methods.
Similar content being viewed by others
References
Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition, CVPR, Boston, MA, USA, pp 1–9
Silver D, Huang A, Maddison CJ et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529:484–489
Krizhevsky A, Sutskever I, Hinton GE (2015) ImageNet classification with deep convolutional neural networks. In: 26th annual conference on neural information processing systems, Lake Tahoe, Nevada, United States, pp 1106–1114
Haijun Z, Yuzhu J, Wang H et al (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl 31(11):7361–7380
Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. http://arxiv.org/abs/1712.04621
Marchesi M (2017) Megapixel size image creation using generative adversarial networks. http://arxiv.org/abs/1706.00082
Lemley J, Bazrafkan S (2017) Peter corcoran, smart augmentation learning an optimal data augmentation strategy. IEEE Access 5:5858–5869
Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov R (2012) Improving neural networks by preventing co-adaptation of feature detectors. http://arxiv.org/abs/1207.0580
Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning, ICML, Lille, France, pp 448–456
Wu Y, He K (2018) Group normalization. In: 15th European conference, Munich, Germany, September 8–14, Proceedings, Part XIII, pp 3–19
Altae-Tran H, Ramsundar B, Pappu AS (2016) Low data drug discovery with one-shot learning. http://arxiv.org/abs/1611.03199
Oreshkin BN, Rodriguez Lopez P, Lacoste A (2018) TADAM: task dependent adaptive metric for improved few-shot learning. In: Annual conference on neural information processing systems, NeurIPS, 3–8 December, Montreal, Canada, pp 719–729
Nichol A, Achiam J, Schulman J (2018) On first-order meta-learning algorithms. http://arxiv.org/abs/1803.02999
Andrychowicz M, Denil M, Gomez Colmenarejo S, Hoffman MW, Pfau D, Schaul T, de Freitas N (2016) Learning to learn by gradient descent by gradient descent. In: Annual conference on neural information processing systems, December 5–10, 2016, Barcelona, Spain, pp 3981–3989
Zhou F, Wu B, Li Z (2018) Deep meta-learning: learning to learn in the concept space. http://arxiv.org/abs/1802.03596
Li Z, Zhou F, Chen F, Li H (2017) Meta-SGD: learning to learn quickly for few shot learning. http://arxiv.org/abs/1707.09835
Mao J, Wei X, Yang Y et al (2015) Learning like a child: fast novel visual concept learning from sentence descriptions of images. In: 27th annual conference on neural information processing systems. In: IEEE international conference on computer vision, ICCV, Santiago, Chile, pp 2533–2541
Chen WY, Liu YC, Kira Z et al (2019) A closer look at few-shot classification. In: 7th international conference on learning representations, ICLR, New Orleans, LA, USA
Jiang X, Havaei M, Varno F et al (2019) Learning to learn with conditional class dependencies. In: 7th international conference on learning representations, ICLR, New Orleans, LA, USA
Lake B, Salakhutdinov R, Gross J et al (2011) One shot learning of simple visual concepts. In: Proceedings of the annual meeting of the cognitive science society, vol 33
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, ICML, Sydney, NSW, Australia, pp 1126–1135
Lee Y, Choi S (2018), Gradient-based meta-learning with learned layerwise metric and subspace. In: Proceedings of the 35th international conference on machine learning, ICML, Stockholmsmassan, Stockholm, Sweden, pp 2933–2942
Jiang X, Havaei M, Varno F, Chartrand G, Chapados N, Matwin S (2019) Learning to learn with conditional class dependencies. In: 7th international conference on learning representations, ICLR 2019, New Orleans, LA, USA
Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. In: Annual conference on neural information processing systems, Long Beach, CA, USA, pp 4077–4087
Ren M, Triantallou E, Ravi S et al (2018) Meta-learning for semi-supervised few-shot classification. In: 6th international conference on learning representations, ICLR, Vancouver, BC, Canada
Fort S (2018) Gaussian prototypical networks for few-shot learning on omniglot. http://arxiv.org/abs/1708.02735
Wang YX, Girshick RB, Hebert M et al (2018) Low-shot learning from imaginary data. In: IEEE conference on computer vision and pattern recognition, CVPR, Salt Lake City, UT, USA, pp 7278–7286
Gregory K, Richard Z, Ruslan S (2015) Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop
Vinyals O, Blundell C, Lillicrap T et al (2016) Matching networks for one shot learning. In: Annual conference on neural information processing systems, Barcelona, Spain, pp 3630–3638
Sung F, Yang Y, Zhang L et al (2018) Learning to compare: relation network for few-shot learning. In: IEEE conference on computer vision and pattern recognition, CVPR, Salt Lake City, UT, USA, pp 1199–1208
Liu Y, Lee J, Park M et al (2018) Learning to propagate labels: transductive propagation network for few-shot learning. In: 7th international conference on learning representations, ICLR, New Orleans, LA, USA
Zhang H, Koniusz P (2019) Power normalizing second-order similarity network for few-shot learning. In: IEEE winter conference on applications of computer vision, WACV, Waikoloa Village, HI, USA, pp 1185–1193
Li FF, Fergus R, Perona P (2003) A bayesian approach to unsupervised one-shot learning of object categories. In: 9th IEEE international conference on computer vision ICCV, Nice, France, pp 1134–1141
Li FF, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell 28:594–611
Lake BM, Salakhutdinov R, Tenenbaum JB (2013) One-shot learning by inverting a compositional causal process. In: 27th annual conference on neural information processing systems, Lake Tahoe, Nevada, United States, pp 2526–2534
Hilliard N, Phillips L, Howland S et al (2018) Few-shot learning with metric-agnostic conditional embeddings. http://arxiv.org/abs/1802.04376
Ravi S, Larochelle H (2017) Optimization as a model for few-shot learning. In: 5th international conference on learning representations, ICLR 2017, Toulon, France
Triantallou E, Zemel RS, Urtasun R (2017) Few-shot learning through an information retrieval lens. In: Annual conference on neural information processing systems, Long Beach, CA, pp 2255–2265
Ye M, Guo Y (2018) Deep triplet ranking networks for one-shot recognition. http://arxiv.org/abs/1804.07275
Finn C, Xu K, Levine S (2018), Probabilistic model-agnostic meta-learning. In: Annual conference on neural information processing systems, NeurIPS, Montreal, Canada, pp 9537–9548
Rusu AA, Rao D, Sygnowski J et al (2019), Meta-learning with latent embedding optimization. In: 7th international conference on learning representations, ICLR, New Orleans, LA, USA
Lim JJ, Salakhutdinov R, Torralba A (2011) Transfer learning by borrowing examples for multi-class object detection. In: 25th annual conference on neural information processing systems, Granada, Spain, pp 118–126
Long L, Wang W, Wen J et al (2018) Object-level representation learning for few-shot image classification. http://arxiv.org/abs/1805.10777
Zhang R, Che T, Ghahramani Z et al (2018) MetaGAN: an adversarial approach to few-shot learning. In: 7 Advances in neural information processing systems, NeurIPS, Montreal, Canada, pp 2371–2380
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations, ICLR, San Diego, CA, USA
Abadi M, Barham P, Chen J et al (2016) Tensorflow: a system for large-scale machine learning. In: 12th fUSENIXg symposium on operating systems design and implementation (OSDI), vol 16, pp 265–283
Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap TP (2016) One-shot learning with memory-augmented neural networks. http://arxiv.org/abs/1605.06065
Acknowledgements
This work was financially supported by The Science and Technology Service Network (STS) Double Innovation project of the Chinese Academy of Sciences, the construction and application of the comprehensive management service platform for urban intelligent business travel (Grant No. KFJ-STS-SCYD-017).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared no potential conflict of interest with respect to the research, authorship, and/or publication of this article.
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
Li, W., Wu, Z., Zhang, J. et al. LGSim: local task-invariant and global task-specific similarity for few-shot classification. Neural Comput & Applic 32, 13065–13076 (2020). https://doi.org/10.1007/s00521-020-04750-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-04750-9