Abstract
Out-of-distribution detection (OOD) deals with anomalous input to neural networks. In the past, specialized methods have been proposed to identify anomalous input. Similarly, it was shown that feature extraction models in combination with outlier detection algorithms are well suited to detect anomalous input. We use outlier detection algorithms to detect anomalous input as reliable as specialized methods from the field of OOD. No neural network adaptation is required; detection is based on the model’s softmax score. Our approach works unsupervised using an Isolation Forest and can be further improved by using a supervised learning method such as Gradient Boosting.
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
Notes
- 1.
- 2.
References
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete Problems in AI Safety (2016)
Bergman, L., Cohen, N., Hoshen, Y.: Deep Nearest Neighbor Anomaly Detection (2020)
Chen, J., Li, Y., Wu, X., Liang, Y., Jha, S.: Robust out-of-distribution detection for neural networks. https://arxiv.org/pdf/2003.09711
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learning, pp. 1321–1330 (2017). http://proceedings.mlr.press/v70/guo17a.html
DeVries, T., Taylor, G.W.: Learning Confidence for Out-of-Distribution Detection in Neural Networks (2018)
Friedman, J.H.: Stochastic gradient boosting. Comput. Stat. Data Anal. 38(4), 367–378 (2002). https://doi.org/10.1016/S0167-9473(01)00065-2. https://www.sciencedirect.com/science/article/pii/S0167947301000652
Hawkins, D.M.: Identification of Outliers, vol. 11. Chapman and Hall, London (1980). https://link.springer.com/content/pdf/10.1007/978-94-015-3994-4.pdf
Hendrycks, D., Gimpel, K.: A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks (2016)
Hendrycks, D., Mazeika, M., Dietterich, T.: Deep Anomaly Detection with Outlier Exposure (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. https://arxiv.org/pdf/1412.6980
Zhang, K., Schölkopf, B., Muandet, K., Wang, Z.: Domain adaptation under target and conditional shift. In: International Conference on Machine Learning, pp. 819–827 (2013). http://proceedings.mlr.press/v28/zhang13d.html
Liang, S., Li, Y., Srikant, R.: Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks (2017)
Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: Giannotti, F. (ed.) Eighth IEEE International Conference on Data Mining, 2008. IEEE, Piscataway (2008). https://doi.org/10.1109/icdm.2008.17
Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 – mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446–461. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_29
Niculescu-Mizil, A., Caruana, R.: Predicting good probabilities with supervised learning. In: Dzeroski, S. (ed.) Proceedings of the 22nd International Conference on Machine Learning. ACM, New York (2005). https://doi.org/10.1145/1102351.1102430
Ren, J., et al.: Likelihood ratios for out-of-distribution detection. https://arxiv.org/pdf/1906.02845
Ruff, L., Vandermeulen, R.A., Franks, B.J., Müller, K.R., Kloft, M.: Rethinking assumptions in deep anomaly detection. https://arxiv.org/pdf/2006.00339
Sun, Y., Guo, C., Li, Y.: React: out-of-distribution detection with rectified activations. arXiv abs/2111.12797 (2021)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 29th IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Piscataway (2016). https://doi.org/10.1109/cvpr.2016.308
Tan, M., Le, V.Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning (2019). https://arxiv.org/pdf/1905.11946
Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images (01072020). https://groups.csail.mit.edu/vision/TinyImages/
Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: a large data set for nonparametric object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 30(11), 1958–1970 (2008). https://doi.org/10.1109/tpami.2008.128
Wang, H., Bah, M.J., Hammad, M.: Progress in outlier detection techniques: a survey. IEEE Access 7, 107964–108000 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Diers, J., Pigorsch, C. (2022). Out-of-Distribution Detection Using Outlier Detection Methods. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds) Image Analysis and Processing – ICIAP 2022. ICIAP 2022. Lecture Notes in Computer Science, vol 13233. Springer, Cham. https://doi.org/10.1007/978-3-031-06433-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-06433-3_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06432-6
Online ISBN: 978-3-031-06433-3
eBook Packages: Computer ScienceComputer Science (R0)