Abstract
Open-world semi-supervised learning differs from traditional semi-supervised learning by allowing labeled and unlabeled data from different data distributions, i.e., unlabeled data may contain novel classes. The goal is to identify samples of known classes while simultaneously detecting and clustering samples of novel classes found in the unlabeled data. To address this challenging task, we propose a novel open-world semi-supervised learning model, which integrates two new confidence-guided techniques to better leverage unlabeled data, especially those from novel classes. Specifically, we first approximate the confidence of model on unlabeled samples by inspecting the prediction consistency through the training process, which guides the temperature scaling for cross-entropy loss. Then, we introduce an adaptive class-specific reweighting contrastive learning method, which further synchronizes the learning speed of known and unknown classes, while reducing the influence of noisy labels. Extensive empirical results show our approach achieves significant performance improvement in both seen and unseen classes compared with previous studies, especially in challenging scenarios with limited labeled data.
This work is partially supported by National Natural Science Foundation of China (Grants no. 62176271), and Science and Technology Program of Guangzhou (Grant no. 202201011681).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asano, Y.M., Rupprecht, C., Vedaldi, A.: Self-labelling via simultaneous clustering and representation learning. In: International Conference on Learning Representations (ICLR) (2020)
Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.A.: Mixmatch: a holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Cao, K., Brbić, M., Leskovec, J.: Open-world semi-supervised learning. In: International Conference on Learning Representations (ICLR) (2022)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9912–9924 (2020)
Chen, H., et al.: Softmatch: addressing the quantity-quality trade-off in semi-supervised learning. arXiv preprint arXiv:2301.10921 (2023)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR (2020)
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Advances in Neural Information Processing Systems, vol. 26 (2013)
Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1422–1430 (2015)
Fini, E., Sangineto, E., Lathuilière, S., Zhong, Z., Nabi, M., Ricci, E.: A unified objective for novel class discovery. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9284–9292 (2021)
Guo, L.Z., Zhang, Y.G., Wu, Z.F., Shao, J.J., Li, Y.F.: Robust semi-supervised learning when not all classes have labels. In: Advances in Neural Information Processing Systems, vol. 35, pp. 3305–3317 (2022)
Guo, L.Z., Zhang, Z.Y., Jiang, Y., Li, Y.F., Zhou, Z.H.: Safe deep semi-supervised learning for unseen-class unlabeled data. In: International Conference on Machine Learning, pp. 3897–3906. PMLR (2020)
Han, K., Rebuffi, S.A., Ehrhardt, S., Vedaldi, A., Zisserman, A.: Automatically discovering and learning new visual categories with ranking statistics. arXiv preprint arXiv:2002.05714 (2020)
Han, K., Vedaldi, A., Zisserman, A.: Learning to discover novel visual categories via deep transfer clustering. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8401–8409 (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS’15 Proceedings of the 28th International Conference on Neural Information Processing Systems, vol. 2, pp. 287–295 (2015)
Hsu, Y.C., Lv, Z., Kira, Z.: Learning to cluster in order to transfer across domains and tasks. arXiv preprint arXiv:1711.10125 (2017)
Huang, L., Zhang, C., Zhang, H.: Self-adaptive training: beyond empirical risk minimization. In: Advances in Neural Information Processing Systems, vol. 33, pp. 19365–19376 (2020)
Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1–2), 83–97 (1955)
Rizve, M.N., Kardan, N., Khan, S., Shahbaz Khan, F., Shah, M.: OpenLDN: learning to discover novel classes for open-world semi-supervised learning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13691, pp. 382–401. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19821-2_22
Rizve, M.N., Kardan, N., Shah, M.: Towards realistic semi-supervised learning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXXI. LNCS, vol. 13691, pp. 437–455. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19821-2_25
Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems, vol. 33, pp. 596–608 (2020)
Sun, Y., Li, Y.: OpenCon: open-world contrastive learning. Trans. Mach. Learn. Res. (2023). https://openreview.net/forum?id=2wWJxtpFer
Vaze, S., Han, K., Vedaldi, A., Zisserman, A.: Generalized category discovery. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7492–7501 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, J., Yang, M., Feng, M. (2024). Confidence-Guided Open-World Semi-supervised Learning. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14428. Springer, Singapore. https://doi.org/10.1007/978-981-99-8462-6_8
Download citation
DOI: https://doi.org/10.1007/978-981-99-8462-6_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8461-9
Online ISBN: 978-981-99-8462-6
eBook Packages: Computer ScienceComputer Science (R0)