Abstract
Many artificial neural network classifiers assume a closed-world, where the composition of classes is fixed and known, however problems where this assumption does not hold are found in nearly every case where multi-class classification is applied. For example, in network traffic classification the actual number of classes often dramatically exceeds the number of classes known or labelled at training time. Various treatments have been proposed to adapt closed-set classifiers for application in open-set scenarios, both formal and informal. To demonstrate the effectiveness of these treatments, we conducted an empirical study using a simple example based on the MNIST digit classification problem. Our results show the various treatments make trade-offs between classification recall and precision. We demonstrate that softmax output equalisation during training can significantly improve performance in open set classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aceto, G., Ciuonzo, D., Montieri, A., Pescapè, A.: Mobile encrypted traffic classification using deep learning. In: 2018 Network Traffic Measurement and Analysis Conference (TMA), pp. 1–8 (2018)
Bendale, A.: abhijitbendale/OSDN (2016). https://github.com/abhijitbendale/OSDN. Accessed 17 June 2019
Bendale, A., Boult, T.E.: Towards open set deep networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1563–1572 (2016)
Dhamija, A.R., Günther, M., Boult, T.E.: Reducing network agnostophobia. CoRR abs/1811.04110 (2018). http://arxiv.org/abs/1811.04110
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks (2016)
LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010). http://yann.lecun.com/exdb/mnist/
Li, Y., et al.: Deep content: unveiling video streaming content from encrypted wifi traffic. In: 2018 IEEE 17th International Symposium on Network Computing and Applications (NCA), pp. 1–8 (2018)
van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008). http://www.jmlr.org/papers/v9/vandermaaten08a.html
Prakhya, S., Venkataram, V., Kalita, J.: Open set text classification using convolutional neural networks. In: International Conference on Natural Language Processing, December 2017. http://par.nsf.gov/biblio/10059464
Rocha, A., Goldenstein, S.: Multi-class from binary - divide to conquer. In: VISAPP (2009)
Scheirer, W., Rocha, A., Sapkota, A., Boult, T.: Toward open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1757–1772 (2013). https://doi.org/10.1109/TPAMI.2012.256
Schuster, R., Shmatikov, V., Tromer, E.: Beauty and the burst: remote identification of encrypted video streams. In: USENIX Security Symposium (2017)
Sensoy, M., Kaplan, L., Kandemir, M.: Evidential deep learning to quantify classification uncertainty. In: Proceedings of the 32Nd International Conference on Neural Information Processing Systems, NIPS 2018, pp. 3183–3193. Curran Associates Inc., USA (2018). http://dl.acm.org/citation.cfm?id=3327144.3327239
Sopyła, K.: ksopyla/tensorflow-mnist-convnets (2017). Accessed 1 May 2019
Zhang, J., Chen, X., Xiang, Y., Zhou, W., Wu, J.: Robust network traffic classification. IEEE/ACM Trans. Netw. 23, 1 (2014). https://doi.org/10.1109/TNET.2014.2320577. http://nsclab.org/nsclab/esi/tonzhang2015.pdf
Zhou, X.S., Huang, T.S.: Small sample learning during multimedia retrieval using biasmap. In: CVPR (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Commonwealth of Australia
About this paper
Cite this paper
Webb, D. (2019). Applying Softmax Classifiers to Open Set. In: Le, T., et al. Data Mining. AusDM 2019. Communications in Computer and Information Science, vol 1127. Springer, Singapore. https://doi.org/10.1007/978-981-15-1699-3_9
Download citation
DOI: https://doi.org/10.1007/978-981-15-1699-3_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1698-6
Online ISBN: 978-981-15-1699-3
eBook Packages: Computer ScienceComputer Science (R0)