Abstract
The open-set recognition task is proposed to handle unknown classes that do not belong to any of the classes in training set. The methods should reject unknown samples while maintaining high classification accuracy on the known classes. Previous methods are divided into two stages, including open-set identification and closed-set classification. These methods usually reject unknown samples according to the previous analysis of the known classes. However, this would inevitably cause risks if the discriminative representation from the unknown classes is insufficient. In contrast to the previous methods, we propose a new method which uses a dual probability distribution to represent the unknowns. From the dual distribution, the boundary of known space is naturally derived, thereby helping identify the unknowns without staging or thresholding. Following this formulation, this paper proposed a new method called Dual Probability Learning Model (DPLM). The model built a neural Gaussian Mixed Model for probability estimation. To learn this model, we also added the normalized joint probability of latent representations into the objective function in the training stage. The results showed that the proposed method is highly effective.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ager, S.: Omniglot writing systems and languages of the world (2008). Accessed 27 Jan 2008
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)
Chen, G., et al.: Learning open set network with discriminative reciprocal points (2020). arXiv preprint arXiv:2011.00178
Ge, Z., Demyanov, S., Chen, Z., Garnavi, R.: Generative openmax for multi-class open set classification (2017). arXiv preprint arXiv:1707.07418
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local relation networks for image recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)
Krizhevsky, A., Hinton, G.: Convolutional deep belief networks on cifar-10. Unpublished Manuscript 40(7), 1–9 (2010)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: The mnist database of handwritten digits. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791
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)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
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)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
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 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint arXiv:1409.1556
Sun, X., Yang, Z., Zhang, C., Ling, K.V., Peng, G.: Conditional gaussian distribution learning for open set recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13480–13489 (2020)
Yoshihashi, R., Shao, W., Kawakami, R., You, S., Iida, M., Naemura, T.: Classification-reconstruction learning for open-set recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4016–4025 (2019)
Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: Lsun: construction of a large-scale image dataset using deep learning with humans in the loop (2015). arXiv preprint arXiv:1506.03365
Zhang, H., Li, A., Guo, J., Guo, Y.: Hybrid models for open set recognition (2020). arXiv preprint arXiv:2003.12506
Zong, B., et al.: Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, S., Yang, F. (2021). Open-Set Recognition with Dual Probability Learning. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13110. Springer, Cham. https://doi.org/10.1007/978-3-030-92238-2_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-92238-2_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92237-5
Online ISBN: 978-3-030-92238-2
eBook Packages: Computer ScienceComputer Science (R0)