Advertisement

Task-Adaptive Feature Reweighting for Few Shot Classification

  • Nan Lai
  • Meina Kan
  • Shiguang ShanEmail author
  • Xilin Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11364)

Abstract

Few shot classification remains a quite challenging problem due to lacking data to train an effective classifier. Lately a few works employ the meta learning schema to learn a generalized feature encoder or distance metric, which is directly used for those unseen classes. In these approaches, the feature representation of a class remains the same even in different tasks (In meta learning, a task of few shot classification involves a set of labeled examples (support set) and a set of unlabeled examples (query set) to be classified. The goal is to get a classifier for the classes in the support set.), i.e. the feature encoder cannot adapt to different tasks. As well known, when distinguishing a class from different classes, the most discriminative feature may be different. Following this intuition, this work proposes a task-adaptive feature reweighting strategy within the framework of recently proposed prototypical network [6]. By considering the relationship between classes in a task, our method generates a feature weight for each class to highlight those features that can better distinguish it from the rest ones. As a result, each class has its own specific feature weight, and this weight is adaptively different in different tasks. The proposed method is evaluated on two few shot classification benchmarks, miniImageNet and tieredImageNet. The experiment results show that our method outperforms the state-of-the-art works demonstrating its effectiveness.

Keywords

Few shot classification Feature reweighting Meta-learning 

Notes

Acknowledgements

This work was partially supported by National Key R&D Program of China under contracts No.2017YFA0700804 and Natural Science Foundation of China under contracts Nos. 61650202, 61772496, 61402443 and 61532018.

References

  1. 1.
    Krizhevsky A., Sutskever I., Hinton G.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2012)Google Scholar
  2. 2.
    Szegedy C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)Google Scholar
  3. 3.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)Google Scholar
  4. 4.
    Huang, G., Liu, Z., Maaten, L., Weinberger, K.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  5. 5.
    Xu, Z., Zhu, L., Yang, Y.: Few-shot object recognition from machine-labeled web images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  6. 6.
    Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems (NIPS) (2017)Google Scholar
  7. 7.
    Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. In: International Conference on Machine Learning (ICML) (2016)Google Scholar
  8. 8.
    Yoo, D., Fan, H., Boddeti, V., Kitani, K.: Efficient k-shot learning with regularized deep networks. In: AAAI Conference on Artificial Intelligence (AAAI) (2018)Google Scholar
  9. 9.
    Li, Z., Zhou, F., Chen, F., Li, H.: Meta-SGD: Learning to Learn Quickly for Few Shot Learning. CoRR abs/1707.09835 (2017)Google Scholar
  10. 10.
    Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning (ICML) (2017)Google Scholar
  11. 11.
    Wong, A., Yuille, A.: One shot learning via compositions of meaningful patches. In: IEEE International Conference on Computer Vision (ICCV) (2015)Google Scholar
  12. 12.
    Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems (NIPS) (2016)Google Scholar
  13. 13.
    Satorras V., Estrach J.: Few-shot learning with graph neural networks. In: International Conference on Learning Representations (ICLR) (2018)Google Scholar
  14. 14.
    Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P., Hospedales, T.: Learning to compare: relation network for few-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  15. 15.
    Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Workshop on Deep Learning (2015)Google Scholar
  16. 16.
    Lake, B., Salakhutdinov, R., Tenenbaum, J.: Human-level concept learning through probabilistic program induction. Science 350, 1332–1338 (2015)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Salakhutdinov, R., Tenenbaum, J., Torralba, A.: One-shot learning with a hierarchical nonparametric Bayesian model. In: ICML Workshop on Unsupervised and Transfer Learning (2012)Google Scholar
  18. 18.
    Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  19. 19.
    Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems (NIPS) (2014)Google Scholar
  20. 20.
    Li, F., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 28, 594–611 (2006)Google Scholar
  21. 21.
    Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. In: International Conference on Learning Representations (ICLR) (2018)Google Scholar
  22. 22.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115, 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Guo, L., Zhang, L.: One-shot Face Recognition by Promoting Underrepresented Classes. CoRR abs/1707.05574 (2017)Google Scholar
  24. 24.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS) (2014)Google Scholar
  25. 25.
    Rezende, D., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: International Conference on Machine Learning (ICML) (2014)Google Scholar
  26. 26.
    Mirza, M., Osindero, S.: Conditional Generative Adversarial Nets. CoRR abs/1411.1784 (2014)Google Scholar
  27. 27.
    Radford, A., Metz, L., Chintala, S.: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. CoRR abs/1511.06434 (2015)Google Scholar
  28. 28.
    Mao, X., Li, Q., Xie, H., Lau, R., Wang, Z., Smolley, S.: Least squares generative adversarial networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  29. 29.
    Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein GANs. In: Advances in Neural Information Processing Systems (NIPS) (2017)Google Scholar
  30. 30.
    Simonyan, K., Vedaldi, A., Zisserman, A.: Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. CoRR abs/1312.6034 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS)Institute of Computing Technology, CASBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina
  3. 3.CAS Center for Excellence in Brain Science and Intelligence TechnologyShanghaiChina

Personalised recommendations