Abstract
In the recent years, researchers proposed a number of successful methods to perform out-of-distribution (OOD) detection in deep neural networks (DNNs). So far the scope of the highly accurate methods has been limited to image level classification tasks. However, attempts for generally applicable methods beyond classification did not attain similar performance. In this paper, we address this limitation by proposing a simple yet effective task-agnostic OOD detection method. We estimate the probability density functions (pdfs) of intermediate features of a pre-trained DNN by performing kernel density estimation (KDE) on the training dataset. As direct application of KDE to feature maps is hindered by their high dimensionality, we use a set of lower-dimensional marginalized KDE models instead of a single high-dimensional one. At test time, we evaluate the pdfs on a test sample and produce a confidence score that indicates the sample is OOD. The use of KDE eliminates the need for making simplifying assumptions about the underlying feature pdfs and makes the proposed method task-agnostic. We perform experiments on classification task using computer vision benchmark datasets. Additionally, we perform experiments on medical image segmentation task using brain MRI datasets. The results demonstrate that the proposed method consistently achieves high OOD detection performance in both classification and segmentation tasks and improves state-of-the-art in almost all cases. Our code is available at https://github.com/eerdil/task_agnostic_ood. Longer version of the paper and supplementary materials can be found as preprint in [8].
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
Notes
- 1.
Pretrained models: https://github.com/pokaxpoka/deep_Mahalanobis_detector.
- 2.
TIN, LSUN, and iSUN are available at https://github.com/facebookresearch/odin.
References
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)
Bishop, C.M.: Novelty detection and neural network validation. IEE Proc.-Vis. Image Sig. Process. 141(4), 217–222 (1994)
Chaitanya, K., Erdil, E., Karani, N., Konukoglu, E.: Contrastive learning of global and local features for medical image segmentation with limited annotations. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Cremers, D., Osher, S.J., Soatto, S.: Kernel density estimation and intrinsic alignment for shape priors in level set segmentation. Int. J. Comput. Vision 69(3), 335–351 (2006). https://doi.org/10.1007/s11263-006-7533-5
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
DeVries, T., Taylor, G.W.: Learning confidence for out-of-distribution detection in neural networks. arXiv preprint arXiv:1802.04865 (2018)
Di Martino, A., et al.: The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol. Psychiatry 19(6), 659–667 (2014)
Erdil, E., Chaitanya, K., Karani, N., Konukoglu, E.: Task-agnostic out-of-distribution detection using kernel density estimation. arXiv preprint arXiv:2006.10712 (2020). https://arxiv.org/pdf/2006.10712.pdf
Erdil, E., Yildirim, S., Tasdizen, T., Cetin, M.: Pseudo-marginal MCMC sampling for image segmentation using nonparametric shape priors. IEEE Trans. Image Process. 28(11), 5702–5715 (2019)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1321–1330. JMLR. org (2017)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: Proceedings of International Conference on Learning Representations (2017)
Hendrycks, D., Mazeika, M., Dietterich, T.: Deep anomaly detection with outlier exposure. In: International Conference on Learning Representations (2018)
Hendrycks, D., Mazeika, M., Kadavath, S., Song, D.: Using self-supervised learning can improve model robustness and uncertainty. In: Advances in Neural Information Processing Systems, pp. 15637–15648 (2019)
Hsu, Y.C., Shen, Y., Jin, H., Kira, Z.: Generalized ODIN: detecting out-of-distribution image without learning from out-of-distribution data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10951–10960 (2020)
Karani, N., Erdil, E., Chaitanya, K., Konukoglu, E.: Test-time adaptable neural networks for robust medical image segmentation. Med. Image Anal. 68, 101907 (2021)
Kim, J., Çetin, M., Willsky, A.S.: Nonparametric shape priors for active contour-based image segmentation. Signal Process. 87(12), 3021–3044 (2007)
Kim, K.H., Shim, S., Lim, Y., Jeon, J., Choi, J., Kim, B., Yoon, A.S.: Rapp: novelty detection with reconstruction along projection pathway. In: International Conference on Learning Representations (2020)
Kohl, S.A., et al.: A probabilistic U-Net for segmentation of ambiguous images. arXiv preprint arXiv:1806.05034 (2018)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples. In: ICLR 2018 (2018)
Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: Advances in Neural Information Processing Systems, pp. 7167–7177 (2018)
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690 (2017)
Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Nalisnick, E., Matsukawa, A., Teh, Y.W., Gorur, D., Lakshminarayanan, B.: Do deep generative models know what they don’t know? In: International Conference on Learning Representations (2018)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Scott, D.W.: Multivariate Density Estimation: Theory, Practice, and Visualization. Wiley, Hoboken (2015)
Silverman, B.W.: Density Estimation for Statistics and Data Analysis, vol. 26. CRC Press, Boco Raton (1986)
Van Essen, D.C., et al.: The WU-MINN human connectome project: an overview. Neuroimage 80, 62–79 (2013)
Venkatakrishnan, A.R., Kim, S.T., Eisawy, R., Pfister, F., Navab, N.: Self-supervised out-of-distribution detection in brain CT scans. arXiv preprint arXiv:2011.05428 (2020)
Vyas, A., Jammalamadaka, N., Zhu, X., Das, D., Kaul, B., Willke, T.L.: Out-of-distribution detection using an ensemble of self supervised leave-out classifiers. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 560–574. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_34
Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)
Xu, P., Ehinger, K.A., Zhang, Y., Finkelstein, A., Kulkarni, S.R., Xiao, J.: TurkerGaze: crowdsourcing saliency with webcam based eye tracking. arXiv preprint arXiv:1504.06755 (2015)
Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)
Yu, Q., Aizawa, K.: Unsupervised out-of-distribution detection by maximum classifier discrepancy. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9518–9526 (2019)
Acknowledgement
The presented work was partly funding by: 1. Personalized Health and Related Technologies (PHRT), project number 222, ETH domain, 2. Clinical Research Priority Program Grant on Artificial Intelligence in Oncological Imaging Network, University of Zurich, 3. Swiss Data Science Center (DeepMicroIA), 4. Swiss Platform for Advanced Scientific Computing (PASC), coordinated by Swiss National Super-computing Centre (CSCS). We also thank Nvidia for their GPU donation.
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
Erdil, E., Chaitanya, K., Karani, N., Konukoglu, E. (2021). Task-Agnostic Out-of-Distribution Detection Using Kernel Density Estimation. In: Sudre, C.H., et al. Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, and Perinatal Imaging, Placental and Preterm Image Analysis. UNSURE PIPPI 2021 2021. Lecture Notes in Computer Science(), vol 12959. Springer, Cham. https://doi.org/10.1007/978-3-030-87735-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-87735-4_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87734-7
Online ISBN: 978-3-030-87735-4
eBook Packages: Computer ScienceComputer Science (R0)
