Abstract
The objective of open set recognition (OSR) is to classify the known classes as well as the unknown classes when the collected samples cannot exhaust all the classes. This paper proposes a loss extension that emphasizes features with larger and smaller magnitudes to find representations that can more effectively separate the known from the unknown classes. Our contributions include: First, we introduce an extension that can be incorporated into different loss functions to find more discriminative representations. Second, we show that the proposed extension can significantly improve the performances of two different types of loss functions on datasets from two different domains. Third, we show that with the proposed extension, one loss function outperforms the others in training time and model accuracy.
Partially supported by grants from Amazon and Rockwell Collins to Philip Chan.
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)
Dhamija, A.R., Günther, M., Boult, T.E.: Reducing network agnostophobia. In: Advances in Neural Information Processing Systems, vol. 31, pp. 9175–9186 (2018)
Gascon, H., Yamaguchi, F., Arp, D., Rieck, K.: Structural detection of android malware using embedded call graphs. In: AISec 2013, pp. 45–54 (2013)
Hassen, M., Chan, P.K.: Scalable function call graph-based malware classification. In: Proceedings ACM 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 SIAM International Conference Data Mining, pp. 154–162 (2020)
Hendrycks, D., Mazeika, M., Dietterich, T.G.: Deep anomaly detection with outlier exposure. In: 7th International Conference on Learning Representations (2019)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
LeCun, Y., Cortes, C., Burges, C.J.: The MNIST database (1999). http://yann.lecun.com/exdb/mnist/
Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples. In: International Conference Learning Representations (2018)
Li, X.-L., Liu, B.: Learning from positive and unlabeled examples with different data distributions. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 218–229. Springer, Heidelberg (2005). https://doi.org/10.1007/11564096_24
Neal, L., Olson, M., Fern, X., Wong, W.-K., Li, F.: Open set learning with counterfactual images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 620–635. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_38
Ortiz, E.G., Becker, B.C.: Face recognition for web-scale datasets. Comput. Vis. Image Underst. 118, 153–170 (2014)
Pidhorskyi, S., Almohsen, R., Doretto, G.: Generative probabilistic novelty detection with adversarial autoencoders. In: NeurIPS, vol. 31, pp. 6823–6834 (2018)
Ronen, R., Radu, M., Feuerstein, C., Yom-Tov, E., Ahmadi, M.: Microsoft malware classification challenge. CoRR arXiv:1802.10135 (2018)
Schlegl, T., Seeböck, P., Waldstein, S.M., Schmidt-Erfurth, U., Langs, G.: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: Information Processing in Medical Imaging, pp. 146–157 (2017)
Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Conference on CVPR, pp. 815–823 (2015)
Schultheiss, A., Käding, C., Freytag, A., Denzler, J.: Finding the unknown: novelty detection with extreme value signatures of deep neural activations. In: Pattern Recognition - 39th German Conference, pp. 226–238 (2017)
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
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Jia, J., Chan, P.K. (2021). MMF: A Loss Extension for Feature Learning in Open Set Recognition. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12892. Springer, Cham. https://doi.org/10.1007/978-3-030-86340-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-86340-1_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86339-5
Online ISBN: 978-3-030-86340-1
eBook Packages: Computer ScienceComputer Science (R0)