{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T06:29:50Z","timestamp":1773124190031,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Excellence Center in Link\u00f6ping-Lund in Information Technology","award":["C08"],"award-info":[{"award-number":["C08"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In order for any learning-based model to be considered reliable, it needs a well-behaved uncertainty or confidence estimate. Most modern neural networks do produce a confidence estimate in the form of their softmax output probability. However, the softmax probability is invalid for out-of-distribution data. Gaussian processes are known to produce a well-behaved confidence estimate that is aware of out-of-distribution samples. Inspired by Gaussian processes, we propose GPify, which combines the softmax probability with a Normalizing Flow in order to add out-of-distribution awareness to the confidence estimate from a neural network. The resulting confidence from GPify is an uncertainty measure that is interpretable and intuitive, while also being probabilistically sound. We evaluate GPify in a selective classification framework, and conclude that it achieves comparable performance to state-of-the-art methods. In addition, we show that GPify has capabilities for detecting adversarial examples, which is a direct improvement over softmax confidence.<\/jats:p>","DOI":"10.1007\/s11263-026-02794-3","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T17:33:39Z","timestamp":1773077619000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GPify: Leveraging the Combined Strength of Normalizing Flow and Softmax For an Out-of-Distribution aware Confidence Score"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-0681","authenticated-orcid":false,"given":"Simon","family":"Kristoffersson Lind","sequence":"first","affiliation":[]},{"given":"Rudolph","family":"Triebel","sequence":"additional","affiliation":[]},{"given":"Volker","family":"Kr\u00fcger","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"issue":"6","key":"2794_CR1","doi-asserted-by":"publisher","first-page":"4403","DOI":"10.1007\/s10462-021-10125-w","volume":"55","author":"A Aldahdooh","year":"2022","unstructured":"Aldahdooh, A., Hamidouche, W., Fezza, S. A., & D\u00e9forges, O. (2022). Adversarial example detection for dnn models: a review and experimental comparison. Artificial Intelligence Review, 55(6), 4403\u20134462. https:\/\/doi.org\/10.1007\/s10462-021-10125-w","journal-title":"Artificial Intelligence Review"},{"key":"2794_CR2","doi-asserted-by":"publisher","unstructured":"Blomqvist, K., Kaski, S., & Heinonen, M. (2020). Deep convolutional gaussian processes. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds.) Machine Learning and Knowledge Discovery in Databases, pp. 582\u2013597. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-46147-8_35.","DOI":"10.1007\/978-3-030-46147-8_35."},{"issue":"53","key":"2794_CR3","first-page":"1605","volume":"11","author":"R El-Yaniv","year":"2010","unstructured":"El-Yaniv, R., & Wiener, Y. (2010). On the foundations of noise-free selective classification. Journal of Machine Learning Research, 11(53), 1605\u20131641.","journal-title":"Journal of Machine Learning Research"},{"key":"2794_CR4","unstructured":"Guo, C., Pleiss, G., Sun, Y., & Weinberger, K.Q. (2017). On calibration of modern neural networks. In: Proceedings of the 34th International Conference on Machine Learning - Volume 70. ICML\u201917, pp. 1321\u20131330. JMLR.org, Sydney, NSW, Australia."},{"key":"2794_CR5","unstructured":"Gardner, J., Pleiss, G., Weinberger, K.Q., Bindel, D., & Wilson, A.G. (2018). Gpytorch: Blackbox matrix-matrix gaussian process inference with gpu acceleration. Advances in neural information processing systems 31."},{"key":"2794_CR6","unstructured":"Goodfellow, I.J., Shlens, J., & Szegedy, C. (2015). Explaining and harnessing adversarial examples arXiv:1412.6572 [stat]."},{"issue":"7","key":"2794_CR7","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1177\/0278364915587924","volume":"35","author":"H Grimmett","year":"2016","unstructured":"Grimmett, H., Triebel, R., Paul, R., & Posner, I. (2016). Introspective classification for robot perception. The International Journal of Robotics Research, 35(7), 743\u2013762. https:\/\/doi.org\/10.1177\/0278364915587924","journal-title":"The International Journal of Robotics Research"},{"key":"2794_CR8","unstructured":"Ho, J., Chen, X., Srinivas, A., Duan, Y., & Abbeel, P. (2019). Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design. arxiv:org\/abs\/1902.00275."},{"key":"2794_CR9","unstructured":"Huang, R., Geng, A., & Li, Y. (2024). On the importance of gradients for detecting distributional shifts in the wild. In: Proceedings of the 35th International Conference on Neural Information Processing Systems. NIPS \u201921, pp. 677\u2013689. Curran Associates Inc., Red Hook, NY, USA."},{"key":"2794_CR10","unstructured":"Izmailov, P., Kirichenko, P., Finzi, M., & Wilson, A.G. (2020). Semi-supervised learning with normalizing flows. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 4615\u20134630. PMLR, https:\/\/proceedings.mlr.press\/v119\/izmailov20a.html."},{"key":"2794_CR11","doi-asserted-by":"publisher","unstructured":"Jain, S., & Argall, B. (2019).Probabilistic human intent recognition for shared autonomy in assistive robotics. J. Hum.-Robot Interact. 9(1), 2\u20131223 https:\/\/doi.org\/10.1145\/3359614.","DOI":"10.1145\/3359614."},{"key":"2794_CR12","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv. arxiv:org\/abs\/1412.6980."},{"key":"2794_CR13","doi-asserted-by":"crossref","unstructured":"Kurakin, A., Goodfellow, I., & Bengio, S. (2017). Adversarial examples in the physical world arXiv:1607.02533 [cs].","DOI":"10.1201\/9781351251389-8"},{"key":"2794_CR14","unstructured":"Krizhevsky, A., Hinton, G., et al. (2009). Learning multiple layers of features from tiny images."},{"key":"2794_CR15","unstructured":"Kirichenko, P., Izmailov, P., & Wilson, A.G. (2020). Why Normalizing Flows Fail to Detect Out-of-Distribution Data. In: Advances in Neural Information Processing Systems, vol. 33, pp. 20578\u201320589. Curran Associates Inc."},{"key":"2794_CR16","doi-asserted-by":"publisher","unstructured":"Kim, J., Koo, J., & Hwang, S. (2023). A unified benchmark for the unknown detection capability of deep neural networks. Expert Systems with Applications 229, 120461 https:\/\/doi.org\/10.1016\/j.eswa.2023.120461.arXiv:2112.00337 [cs].","DOI":"10.1016\/j.eswa.2023.120461."},{"key":"2794_CR17","doi-asserted-by":"publisher","unstructured":"Kristoffersson Lind, S., Triebel, R., Nardi, L., & Krueger, V. (2023). Out-of-distribution detection for adaptive computer vision. In: Gade, R., Felsberg, M., K\u00e4m\u00e4r\u00e4inen, J.-K. (eds.) Image Analysis. Lecture Notes in Computer Science, pp. 311\u2013325. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-31438-4_21.","DOI":"10.1007\/978-3-031-31438-4_21."},{"key":"2794_CR18","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.patrec.2024.09.011","volume":"186","author":"S Kristoffersson Lind","year":"2024","unstructured":"Kristoffersson Lind, S., Xiong, Z., Forss\u00e9n, P.-E., & Kr\u00fcger, V. (2024). Uncertainty quantification metrics for deep regression. Pattern Recognition Letters, 186, 91\u201397. https:\/\/doi.org\/10.1016\/j.patrec.2024.09.011","journal-title":"Pattern Recognition Letters"},{"issue":"11","key":"2794_CR19","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proceedings of the IEEE"},{"key":"2794_CR20","unstructured":"Loshchilov, I., & Hutter, F. (2017). Sgdr: Stochastic gradient descent with warm restarts arXiv:1608.03983 [cs]."},{"key":"2794_CR21","doi-asserted-by":"crossref","unstructured":"Lind, S.K., Triebel, R., & Kr\u00fcger, V. (2024) . Making the flow glow - robot perception under severe lighting conditions using normalizing flow gradients arXiv:2412.07565 [cs].","DOI":"10.1109\/IROS58592.2024.10801601"},{"key":"2794_CR22","unstructured":"Liu, W., Wang, X., Owens, J., & Li, Y. (2020). Energy-based out-of-distribution detection. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21464\u201321475. Curran Associates Inc, https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/f5496252609c43eb8a3d147ab9b9c006-Abstract.html."},{"key":"2794_CR23","unstructured":"McInnes, L., Healy, J., & Melville, J. (2020). Umap: Uniform manifold approximation and projection for dimension reduction arXiv:1802.03426 [stat]."},{"issue":"57","key":"2794_CR24","first-page":"1","volume":"22","author":"G Papamakarios","year":"2021","unstructured":"Papamakarios, G., Nalisnick, E., Rezende, D. J., Mohamed, S., & Lakshminarayanan, B. (2021). Normalizing Flows for Probabilistic Modeling and Inference. Journal of Machine Learning Research, 22(57), 1\u201364.","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"2794_CR25","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., & Fei-Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV), 115(3), 211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"2794_CR26","doi-asserted-by":"publisher","unstructured":"Rasmussen, C.E., & Williams, C.K.I. (2005). Gaussian Processes for Machine Learning. The MIT Press, Cambridge. https:\/\/doi.org\/10.7551\/mitpress\/3206.001.0001.","DOI":"10.7551\/mitpress\/3206.001.0001."},{"key":"2794_CR27","doi-asserted-by":"publisher","first-page":"96331","DOI":"10.1109\/ACCESS.2022.3202545","volume":"10","author":"C Sevastopoulos","year":"2022","unstructured":"Sevastopoulos, C., & Konstantopoulos, S. (2022). A survey of traversability estimation for mobile robots. IEEE Access, 10, 96331\u201396347. https:\/\/doi.org\/10.1109\/ACCESS.2022.3202545","journal-title":"IEEE Access"},{"issue":"11","key":"2794_CR28","first-page":"2881","volume":"33","author":"T Sainburg","year":"2021","unstructured":"Sainburg, T., McInnes, L., & Gentner, T. Q. (2021). Parametric umap embeddings for representation and semisupervised learning. Neural Computation, 33(11), 2881\u20132907.","journal-title":"Neural Computation"},{"key":"2794_CR29","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2014). Intriguing properties of neural networks arXiv:1312.6199 [cs]."},{"key":"2794_CR30","unstructured":"Wilk, M., Rasmussen, C.E., & Hensman, J. (2017). Convolutional gaussian processes. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates Inc, https:\/\/papers.nips.cc\/paper_files\/paper\/2017\/hash\/1c54985e4f95b7819ca0357c0cb9a09f-Abstract.html."},{"key":"2794_CR31","unstructured":"Wenger, J., Kjellstr\u00f6m, H., & Triebel, R. (2020) Non-parametric calibration for classification. In: Chiappa, S., Calandra, R. (eds.) Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 108, pp. 178\u2013190. PMLR, https:\/\/proceedings.mlr.press\/v108\/wenger20a.html."},{"key":"2794_CR32","doi-asserted-by":"publisher","unstructured":"Wang, H., Li, Z., Feng, L., & Zhang, W. (2022). Vim: Out-of-distribution with virtual-logit matching. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4911\u20134920. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00487.https:\/\/ieeexplore.ieee.org\/document\/9879414.","DOI":"10.1109\/CVPR52688.2022.00487."},{"issue":"9","key":"2794_CR33","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.1007\/s11263-024-02029-3","volume":"132","author":"G Xia","year":"2024","unstructured":"Xia, G., & Bouganis, C.-S. (2024). Augmenting the softmax with additional confidence scores for improved selective classification with out-of-distribution data. International Journal of Computer Vision, 132(9), 3714\u20133752. https:\/\/doi.org\/10.1007\/s11263-024-02029-3","journal-title":"International Journal of Computer Vision"},{"issue":"12","key":"2794_CR34","doi-asserted-by":"publisher","first-page":"5635","DOI":"10.1007\/s11263-024-02117-4","volume":"132","author":"J Yang","year":"2024","unstructured":"Yang, J., Zhou, K., Li, Y., & Liu, Z. (2024). Generalized out-of-distribution detection: A survey. International Journal of Computer Vision, 132(12), 5635\u20135662. https:\/\/doi.org\/10.1007\/s11263-024-02117-4","journal-title":"International Journal of Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02794-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02794-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02794-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T17:33:45Z","timestamp":1773077625000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02794-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2794"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02794-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]},"assertion":[{"value":"12 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"185"}}