Abstract
Current supervised deep learning models are shown to achieve exceptional performance when data samples used in evaluation come from a known source, but are susceptible to performance degradations when the data distribution is even slightly shifted. In this work, we study the interaction of two related aspects in this context: (1) out-of-distribution (OOD) generalization ability of DNNs to successfully classify samples from unobserved data distributions, and (2) being able to detect strictly OOD samples when observed at test-time, finding that acquisition of these two capabilities can be at odds. We experimentally analyze the impact of various training data related texture and shape biases on both abilities. Importantly, we reveal that naive outlier exposure mechanisms can help to improve OOD detection performance while introducing strong texture biases that conflict with the generalization abilities of the networks. We further explore the influence of such conflicting texture bias backdoors, which lead to unreliable OOD detection performance on spurious OOD samples observed at test-time.
This work has been supported by the “University SAL Labs” initiative of Silicon Austria Labs (SAL) and its Austrian partner universities for applied fundamental research for electronic based systems.
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
References
Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Computer Vision and Pattern Recognition Workshop (2004)
Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11), 665–673 (2020)
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)
Grathwohl, W., Wang, K.C., Jacobsen, J.H., Duvenaud, D., Norouzi, M., Swersky, K.: Your classifier is secretly an energy based model and you should treat it like one. In: International Conference on Learning Representations (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016)
Hendrycks, D., Mazeika, M., Dietterich, T.: Deep anomaly detection with outlier exposure. In: International Conference on Learning Representations (2019)
Hermann, K., Chen, T., Kornblith, S.: The origins and prevalence of texture bias in convolutional neural networks. Adv. Neural. Inf. Process. Syst. 33, 19000–19015 (2020)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)
Krizhevsky, A.: Learning multiple layers of features from tiny images. Master’s thesis, University of Toronto (2009)
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)
LeCun, Y.: The MNIST database of handwritten digits (1998)
Lee, S., Hwang, I., Kang, G.C., Zhang, B.T.: Improving robustness to texture bias via shape-focused augmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4323–4331 (2022)
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. Adv. Neural. Inf. Process. Syst. 33, 21464–21475 (2020)
Moon, J.H., Ahn, N., Sohn, K.A.: Decomposing texture and semantics for out-of-distribution detection (2022). https://openreview.net/forum?id=UYDtmk6BMf5
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
Ryali, C., Schwab, D.J., Morcos, A.S.: Learning background invariance improves generalization and robustness in self-supervised learning on ImageNet and beyond. In: NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future (2021)
Salehi, M., Mirzaei, H., Hendrycks, D., Li, Y., Rohban, M.H., Sabokrou, M.: A unified survey on anomaly, novelty, open-set, and out-of-distribution detection: solutions and future challenges. arXiv preprint arXiv:2110.14051 (2021)
Sauer, A., Geiger, A.: Counterfactual generative networks. In: International Conference on Learning Representations (2021)
Shen, Z., et al.: Towards out-of-distribution generalization: a survey. arXiv preprint arXiv:2108.13624 (2021)
Sun, Y., Ming, Y., Zhu, X., Li, Y.: Out-of-distribution detection with deep nearest neighbors. In: International Conference on Machine Learning (2022)
Tommasi, T., Patricia, N., Caputo, B., Tuytelaars, T.: A deeper look at dataset bias. In: Csurka, G. (ed.) Domain Adaptation in Computer Vision Applications. ACVPR, pp. 37–55. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58347-1_2
Xiao, K., Engstrom, L., Ilyas, A., Madry, A.: Noise or signal: the role of image backgrounds in object recognition. arXiv preprint arXiv:2006.09994 (2020)
Yang, J., Zhou, K., Li, Y., Liu, Z.: Generalized out-of-distribution detection: a survey. arXiv preprint arXiv:2110.11334 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Klaiber Aboitiz, F.J., Legenstein, R., Özdenizci, O. (2023). Interaction of Generalization and Out-of-Distribution Detection Capabilities in Deep Neural Networks. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14263. Springer, Cham. https://doi.org/10.1007/978-3-031-44204-9_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-44204-9_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44203-2
Online ISBN: 978-3-031-44204-9
eBook Packages: Computer ScienceComputer Science (R0)