Advertisement

Margin Constraint for Low-Shot Learning

  • Xiaotian WuEmail author
  • Yizhuo Wang
Conference paper
  • 100 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12047)

Abstract

Low-shot learning aims to recognize novel visual categories with limited examples, which is mimicking the human visual system and remains a challenging research problem. In this paper, we introduce the margin constraint in loss function for the low-shot learning field to enhance the model’s discriminative power. Additionally, we adopt the novel categories’ normalized feature vectors as the corresponding classification weight vectors directly, in order to provide an instant classification performance on the novel categories without retraining. Experiments show that our method provides a better generalization and outperforms the previous methods on the low-shot leaning benchmarks.

Keywords

Low-shot learning Margin constraint Normalized vectors 

References

  1. 1.
    Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  2. 2.
    Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of International Conference on Machine Learning (2017)Google Scholar
  3. 3.
    Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  4. 4.
    Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  5. 5.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  6. 6.
    Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  7. 7.
    Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: Proceedings of International Conference on Machine Learning Workshop (2015)Google Scholar
  8. 8.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of Conference on Neural Information Processing Systems (2012)Google Scholar
  9. 9.
    Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  10. 10.
    Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: Proceedings of International Conference on Machine Learning (2016)Google Scholar
  11. 11.
    Luo, C., Zhan, J., Xue, X., Wang, L., Ren, R., Yang, Q.: Cosine normalization: using cosine similarity instead of dot product in neural networks. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 382–391. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01418-6_38CrossRefGoogle Scholar
  12. 12.
    Paszke, A., et al.: Automatic differentiation in PyTorch. In: Proceedings of Conference on Neural Information Processing Systems Workshop (2017)Google Scholar
  13. 13.
    Qi, H., Brown, M., Lowe, D.G.: Low-shot learning with imprinted weights. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  14. 14.
    Qiao, S., Liu, C., Shen, W., Yuille, A.L.: Few-shot image recognition by predicting parameters from activations. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  15. 15.
    Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: Proceedings of International Conference on Learning Representations (2017)Google Scholar
  16. 16.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Schmidhuber, J., Zhao, J., Wiering, M.: Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement. Mach. Learn. 28(1), 105–130 (1997)CrossRefGoogle Scholar
  18. 18.
    Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Proceedings of Conference on Neural Information Processing Systems (2017)Google Scholar
  19. 19.
    Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  20. 20.
    Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: Proceedings of Conference on Neural Information Processing Systems (2016)Google Scholar
  21. 21.
    Wah, C., Branson, S., Perona, P., Belongie, S.: Multiclass recognition and part localization with humans in the loop. In: Proceedings of International Conference on Computer Vision (2011)Google Scholar
  22. 22.
    Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926–930 (2018)CrossRefGoogle Scholar
  23. 23.
    Wang, F., Xiang, X., Cheng, J., Yuille, A.L.: NormFace: \({\rm L}_2\) hypersphere embedding for face verification. In: Proceedings of the 25th ACM International Conference on Multimedia (2017)Google Scholar
  24. 24.
    Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. In: Proceedings of Conference on Computer Vision and Pattern Recognition (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Beijing Institute of TechnologyBeijingChina

Personalised recommendations