Abstract
In this paper, we consider the problem of Novel Class Discovery (NCD) in Open Set Recognition (OSR). Given a labeled and an unlabeled set for training, NCD aims to discover the novel categories in the unlabeled set with prior knowledge learned from the labeled set. Existing approaches tackle the NCD problems under a close-set setting, where only the existing categories from the labeled set and the novel categories from the unlabeled set will occur during the inference. This paper considers a more realistic open-set scenario. In the open-set setting, in addition to the existing and novel categories, some unknown categories absent from the training could be present during inference. To address NCD in the open-set scenario, we propose the General Inter-Intra (GII) loss, a unified approach for learning representations from both labeled and unlabeled samples. The proposed approach discovers novel categories in the training set (NCD) meanwhile recognizes the unknown categories (OSR). We evaluate GII with image and graph datasets, and the results indicate that our proposed approach is more effective than other NCD and OSR approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
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)
Chang, J., Wang, L., Meng, G., Xiang, S., Pan, C.: Deep adaptive image clustering. In: IEEE International Conference on Computer Vision, ICCV Italy. IEEE Computer Society, pp. 5880–5888 (2017)
Dhamija, A.R., Günther, M., Boult, T.E.: Reducing network agnostophobia. Adv. Neural Inf. Process. Syst. 31, 9175–9186 (2018)
Gascon, H., Yamaguchi, F., Arp, D., Rieck, K.: Structural detection of android malware using embedded call graphs. In Proceedings of the 2013 ACM Workshop on Artificial Intelligence and Security (AISec), pp. 45–54 (2013)
Ge, Z., Demyanov, S., Garnavi, R.: Generative OpenMax for multi-class open set classification. In: British Machine Vision Conference (2017)
Gupta, D., Ramjee, R., Kwatra, N., Sivathanu, M.: Unsupervised clustering using pseudo-semi-supervised learning. In: 8th International Conference on Learning Representations, ICLR, Ethiopia (2020)
Han, K., Vedaldi, A., Zisserman, A.: Learning to discover novel visual categories via deep transfer clustering. In: IEEE/CVF International Conference on Computer Vision, ICCV, Korea (South). IEEE, 8400–8408 (2019)
Hassen, M., Chan, P.K.: Scalable function call graph-based malware classification. In: Proceedings of the Seventh ACM on Conference on Data and Application Security and Privacy, pp. 239–248 (2017)
Hassen, M., Chan, P.K.: Learning a neural-network-based representation for open set recognition. In: Proceedings of the SIAM International Conference on Data Mining, SDM USA. SIAM, pp. 154–162 (2020a)
Hassen, M., Chan, P.K.: Learning a neural-network-based representation for open set recognition. In: Proceedings of the SIAM International Conference Data Mining (2020), pp. 154–162 (2020b). arxiv:1802.04365
Jia, J., Chan, P.K.: MMF: a loss extension for feature learning in open set recognition. In: International Conference on Artificial Neural Networks. Proceedings Part II, pp. 319–331 (2021)
Jia, J., Chan, P.K.: Feature decoupling in self-supervised representation learning for open set recognition. CoRR abs/2209.14385 (2022). arXiv:2209.14385
Liu, Yu., Tuytelaars, T.: Residual tuning: toward novel category discovery without labels. IEEE Trans. Neural Netw. Learn. Syst. 2022, 1–15 (2022)
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)
Ronen, R., Radu, M., Feuerstein, C., Yom-Tov, E., Ahmadi, M.: . Microsoft malware classification challenge. CoRR abs/1802.10135 (2018). arxiv:1802.10135
Shu, Y., Shi, Y., Wang, Y., Zou, Y., Yuan, Q., Tian, Y.: ODN: opening the deep network for open-set action recognition. In: 2018 International Conference on Multimedia and Expo (ICME), pp. 1–6. . IEEE (2018)
Zhao, B., Han, K.: Novel visual category discovery with dual ranking statistics and mutual knowledge distillation. In: Annual Conference on Neural Information Processing Systems, NeurIPS, virtual, pp. 22982–22994 (2021)
Zhong, Z., Zhu, L., Luo, Z., Li, S., Yang, Y., Sebe, N.: OpenMix: reviving known knowledge for discovering novel visual categories in an open world. In: Conference on Computer Vision and Pattern Recognition, CVPR, virtual. Computer Vision Foundation, pp. 9462–9470. IEEE (2021)
Zhou, Y., Jiang, X.: Android malware genome project (2015). http://www.malgenomeproject.org/
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 Switzerland AG
About this paper
Cite this paper
Jia, J., Chan, P.K. (2023). GII: A Unified Approach to Representation Learning in Open Set Recognition with Novel Category Discovery. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14261. Springer, Cham. https://doi.org/10.1007/978-3-031-44198-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-44198-1_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44197-4
Online ISBN: 978-3-031-44198-1
eBook Packages: Computer ScienceComputer Science (R0)