Abstract
In open set recognition (OSR), the model not only needs to correctly recognize known class samples, but also needs to be able to effectively reject unknown samples. To address this problem, we propose a joint learning model with post-processing based on the concept of Reciprocal Points. Specifically, to guarantee the accuracy of known class recognition, we design a two-branch network containing a self-supervised branch and a classification branch. The self-supervised branch helps the model classify known classes more accurately. Then, to avoid misjudging unknown samples as known ones with high confidence, we carefully redesign the open loss to better separate the known and unknown spaces, and design a post-processing mechanism to penalize the predictions of potential unknown samples. We perform several experiments and ablations on our model, obtaining the state-of-the-art results on most datasets for open set recognition and unknown detection tasks.
This research is supported by National Natural Science Foundation of China (Grant No. 61972271) and Sichuan Science and Technology Program (No. 2022YFS0557).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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., Peng, P., Wang, X., Tian, Y.: Adversarial reciprocal points learning for open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https://doi.org/10.1109/TPAMI.2021.3106743
Chen, G., et al.: Learning open set network with discriminative reciprocal points. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 507–522. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_30
Ge, Z., Demyanov, S., Chen, Z., Garnavi, R.: Generative openmax for multi-class open set classification. In: British Machine Vision Conference 2017. British Machine Vision Association and Society for Pattern Recognition (2017)
Guo, Y., Camporese, G., Yang, W., Sperduti, A., Ballan, L.: Conditional variational capsule network for open set recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 103–111 (2021)
Komodakis, N., Gidaris, S.: Unsupervised representation learning by predicting image rotations. In: International Conference on Learning Representations (ICLR) (2018)
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690 (2017)
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)
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)
Oza, P., Patel, V.M.: C2ae: class conditioned auto-encoder for open-set recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2307–2316 (2019)
Perera, P., et al.: Generative-discriminative feature representations for open-set recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11814–11823 (2020)
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)
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)
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)
Yoshihashi, R., Shao, W., Kawakami, R., You, S., Iida, M., Naemura, T.: Classification-reconstruction learning for open-set recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4016–4025 (2019)
Zhou, D.W., Ye, H.J., Zhan, D.C.: Learning placeholders for open-set recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, Q., Xing, G., Liu, Y. (2023). A Joint Learning Model for Open Set Recognition with Post-processing. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1791. Springer, Singapore. https://doi.org/10.1007/978-981-99-1639-9_35
Download citation
DOI: https://doi.org/10.1007/978-981-99-1639-9_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1638-2
Online ISBN: 978-981-99-1639-9
eBook Packages: Computer ScienceComputer Science (R0)