Advertisement

Learning Open Set Network with Discriminative Reciprocal Points

Conference paper
  • 647 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12348)

Abstract

Open set recognition is an emerging research area that aims to simultaneously classify samples from predefined classes and identify the rest as ‘unknown’. In this process, one of the key challenges is to reduce the risk of generalizing the inherent characteristics of numerous unknown samples learned from a small amount of known data. In this paper, we propose a new concept, Reciprocal Point, which is the potential representation of the extra-class space corresponding to each known category. The sample can be classified to known or unknown by the otherness with reciprocal points. To tackle the open set problem, we offer a novel open space risk regularization term. Based on the bounded space constructed by reciprocal points, the risk of unknown is reduced through multi-category interaction. The novel learning framework called Reciprocal Point Learning (RPL), which can indirectly introduce the unknown information into the learner with only known classes, so as to learn more compact and discriminative representations. Moreover, we further construct a new large-scale challenging aircraft dataset for open set recognition: Aircraft 300 (Air-300). Extensive experiments on multiple benchmark datasets indicate that our framework is significantly superior to other existing approaches and achieves state-of-the-art performance on standard open set benchmarks.

Notes

Acknowledgments

This work is partially supported by grants from the National Key R&D Program of China under grant 2017YFB1002400, the Key-Area Research and Development Program of Guangdong Province under Grant 2019B010153002, and the National Natural Science Foundation of China under contract No. 61825101, No. 61702515 and No. U1611461.

Supplementary material

504435_1_En_30_MOESM1_ESM.pdf (8.4 mb)
Supplementary material 1 (pdf 8596 KB)

References

  1. 1.
    Bartlett, P.L., Wegkamp, M.H.: Classification with a reject option using a hinge loss. J. Mach. Learn. Res. 9, 1823–1840 (2008)MathSciNetzbMATHGoogle Scholar
  2. 2.
    Bendale, A., Boult, T.E.: Towards open set deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1563–1572 (2016)Google Scholar
  3. 3.
    Da, Q., Yu, Y., Zhou, Z.H.: Learning with augmented class by exploiting unlabeled data. In: Twenty-Eighth AAAI Conference on Artificial Intelligence (2014)Google Scholar
  4. 4.
    Davis, J., Goadrich, M.: The relationship between precision-recall and ROC curves. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 233–240. ACM (2006)Google Scholar
  5. 5.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)Google Scholar
  6. 6.
    Dhamija, A.R., Günther, M., Boult, T.: Reducing network agnostophobia. In: Advances in Neural Information Processing Systems, pp. 9157–9168 (2018)Google Scholar
  7. 7.
    Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Ge, Z., Demyanov, S., Chen, Z., Garnavi, R.: Generative OpenMax for multi-class open set classification. arXiv preprint arXiv:1707.07418 (2017)
  9. 9.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)Google Scholar
  10. 10.
    Hein, M., Andriushchenko, M., Bitterwolf, J.: Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 41–50 (2019)Google Scholar
  11. 11.
    Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016)
  12. 12.
    Hendrycks, D., Mazeika, M., Dietterich, T.G.: Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606 (2018)
  13. 13.
    Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report. Citeseer (2009)Google Scholar
  14. 14.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  15. 15.
    Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples. arXiv preprint arXiv:1711.09325 (2017)
  16. 16.
    Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690 (2017)
  17. 17.
    Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. arXiv preprint arXiv:1904.05160 (2019)
  18. 18.
    Nalisnick, E., Matsukawa, A., Teh, Y.W., Gorur, D., Lakshminarayanan, B.: Do deep generative models know what they don’t know? arXiv preprint arXiv:1810.09136 (2018)
  19. 19.
    Neal, L., Olson, M., Fern, X., Wong, W.K., Li, F.: Open set learning with counterfactual images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 613–628 (2018)Google Scholar
  20. 20.
    Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)Google Scholar
  21. 21.
    Oza, P., Patel, V.M.: C2AE: class conditioned auto-encoder for open-set recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2307–2316 (2019)Google Scholar
  22. 22.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Scheirer, W.J., de Rezende Rocha, A., Sapkota, A., Boult, T.E.: Toward open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1757–1772 (2013)CrossRefGoogle Scholar
  24. 24.
    Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46478-7_31CrossRefGoogle Scholar
  25. 25.
    Yang, H.M., Zhang, X.Y., Yin, F., Liu, C.L.: Robust classification with convolutional prototype learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3474–3482 (2018)Google Scholar
  26. 26.
    Yoshihashi, R., Shao, W., Kawakami, R., You, S., Iida, M., Naemura, T.: Classification-reconstruction learning for open-set recognition. arXiv preprint arXiv:1812.04246 (2018)
  27. 27.
    Yuan, M., Wegkamp, M.: Classification methods with reject option based on convex risk minimization. J. Mach. Learn. Res. 11, 111–130 (2010)MathSciNetzbMATHGoogle Scholar
  28. 28.
    Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Computer Science and TechnologyPeking UniversityBeijingChina
  2. 2.State Key Laboratory of Virtual Reality Technology and Systems, SCSEBeihang UniversityBeijingChina
  3. 3.Peng Cheng LaboratoryShenzhenChina
  4. 4.Hikvision Research InstituteHangzhouChina

Personalised recommendations