{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T16:13:10Z","timestamp":1787242390335,"version":"build-2736575974"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132191","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:39:53Z","timestamp":1774543193000},"page":"132191","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Guidelines for the selection, calibration, and evaluation of post-hoc OOD detectors in high-dimensional representations generated by CNN and ViT models in image recognition"],"prefix":"10.1016","volume":"321","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8067-7721","authenticated-orcid":false,"given":"Szymon","family":"Datko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6723-271X","authenticated-orcid":false,"given":"Kamil","family":"Szyc","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7749-4251","authenticated-orcid":false,"given":"Tomasz","family":"Walkowiak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8405-9987","authenticated-orcid":false,"given":"Henryk","family":"Maciejewski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132191_bib0001","series-title":"Proceedings of the 2001 ACM SIGMOD international conference on management of data","first-page":"37","article-title":"Outlier detection for high dimensional data","author":"Aggarwal","year":"2001"},{"issue":"6698","key":"10.1016\/j.eswa.2026.132191_bib0002","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1126\/science.adn0117","article-title":"Managing extreme AI risks amid rapid progress","volume":"384","author":"Bengio","year":"2024","journal-title":"Science"},{"key":"10.1016\/j.eswa.2026.132191_bib0003","unstructured":"Bitterwolf, J., Mueller, M., & Hein, M. (2023). In or out? Fixing imagenet out-of-distribution detection evaluation. arXiv: 2306.00826."},{"key":"10.1016\/j.eswa.2026.132191_bib0004","series-title":"ACM SIGMOD record","first-page":"93","article-title":"LOF: Identifying density-based local outliers","volume":"vol. 29","author":"Breunig","year":"2000"},{"issue":"3","key":"10.1016\/j.eswa.2026.132191_bib0005","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/1541880.1541882","article-title":"Anomaly detection: A survey","volume":"41","author":"Chandola","year":"2009","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.1016\/j.eswa.2026.132191_bib0006","series-title":"Computer vision\u2013ECCV 2020: 16th european conference, glasgow, UK, august 23\u201328, 2020, proceedings, part III 16","first-page":"507","article-title":"Learning open set network with discriminative reciprocal points","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.132191_bib0007","series-title":"Proceedings of the IEEE conf. on computer vision and pattern recognition (CVPR)","article-title":"Describing textures in the wild","author":"Cimpoi","year":"2014"},{"key":"10.1016\/j.eswa.2026.132191_sbref0008","series-title":"Advances in neural information processing systems","first-page":"17744","article-title":"Beyond mahalanobis distance for textual OOD detection","volume":"vol. 35","author":"Colombo","year":"2022"},{"key":"10.1016\/j.eswa.2026.132191_bib0009","series-title":"2009 IEEE conference on computer vision and pattern recognition","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.eswa.2026.132191_bib0010","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.neucom.2013.12.002","article-title":"An experimental evaluation of novelty detection methods","volume":"135","author":"Ding","year":"2014","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.132191_bib0011","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv: 2010.11929."},{"key":"10.1016\/j.eswa.2026.132191_bib0012","unstructured":"Du, X., Wang, Z., Cai, M., & Li, Y. (2022). Vos: Learning what you don\u2019t know by virtual outlier synthesis. arXiv: 2202.01197."},{"key":"10.1016\/j.eswa.2026.132191_bib0013","first-page":"7068","article-title":"Exploring the limits of out-of-distribution detection","volume":"34","author":"Fort","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132191_bib0014","doi-asserted-by":"crossref","first-page":"32142","DOI":"10.52202\/068431-2329","article-title":"Adbench: Anomaly detection benchmark","volume":"35","author":"Han","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132191_bib0015","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.eswa.2026.132191_bib0016","series-title":"International conference on machine learning","first-page":"8759","article-title":"Scaling out-of-distribution detection for real-world settings","author":"Hendrycks","year":"2022"},{"key":"10.1016\/j.eswa.2026.132191_bib0017","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"8340","article-title":"The many faces of robustness: A critical analysis of out-of-distribution generalization","author":"Hendrycks","year":"2021"},{"key":"10.1016\/j.eswa.2026.132191_bib0018","unstructured":"Hendrycks, D., Carlini, N., Schulman, J., & Steinhardt, J. (2021b). Unsolved problems in ML safety. arXiv: 2109.13916."},{"key":"10.1016\/j.eswa.2026.132191_bib0019","series-title":"International conference on learning representations","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2017"},{"key":"10.1016\/j.eswa.2026.132191_bib0020","unstructured":"Hendrycks, D., Mazeika, M., & Dietterich, T. (2018). Deep anomaly detection with outlier exposure. arXiv: 1812.04606."},{"key":"10.1016\/j.eswa.2026.132191_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15262","article-title":"Natural adversarial examples","author":"Hendrycks","year":"2021"},{"key":"10.1016\/j.eswa.2026.132191_bib0022","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"1314","article-title":"Searching for mobilenetv3","author":"Howard","year":"2019"},{"key":"10.1016\/j.eswa.2026.132191_bib0023","unstructured":"Ilharco, G., Wortsman, M., Wightman, R., Gordon, C., Carlini, N., Taori, R., Dave, A., Shankar, V., Namkoong, H., Miller, J., Hajishirzi, H., Farhadi, A., & Schmidt, L. (2021). OpenCLIP. If you use this software, please cite it as below.10.5281\/zenodo.5143773."},{"key":"10.1016\/j.eswa.2026.132191_bib0024","series-title":"Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining","first-page":"444","article-title":"Angle-based outlier detection in high-dimensional data","author":"Kriegel","year":"2008"},{"key":"10.1016\/j.eswa.2026.132191_bib0025","series-title":"Proceedings of the 32nd international conference on neural information processing systems","first-page":"7167-7177","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"Lee","year":"2018"},{"key":"10.1016\/j.eswa.2026.132191_bib0026","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8798","article-title":"Few-shot open-set recognition using meta-learning","author":"Liu","year":"2020"},{"key":"10.1016\/j.eswa.2026.132191_bib0027","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume":"33","author":"Liu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132191_bib0028","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12009","article-title":"Swin transformer v2: Scaling up capacity and resolution","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132191_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132191_bib0030","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"116","article-title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","author":"Ma","year":"2018"},{"key":"10.1016\/j.eswa.2026.132191_bib0031","series-title":"Computational science\u2013ICCS 2022: 22nd international conference, London, UK, june 21\u201323, 2022, proceedings, part I","first-page":"262","article-title":"Out-of-distribution detection in high-dimensional data using mahalanobis distance-critical analysis","author":"Maciejewski","year":"2022"},{"key":"10.1016\/j.eswa.2026.132191_bib0032","series-title":"Proceedings of the 26th international joint conference on artificial intelligence","first-page":"4745","article-title":"Concrete problems for autonomous vehicle safety: Advantages of bayesian deep learning","author":"McAllister","year":"2017"},{"key":"10.1016\/j.eswa.2026.132191_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2022.103996","article-title":"Evaluating pointwise reliability of machine learning prediction","volume":"127","author":"Nicora","year":"2022","journal-title":"Journal of Biomedical Informatics"},{"key":"10.1016\/j.eswa.2026.132191_bib0034","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.eswa.2026.132191_bib0035","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13675","article-title":"Revisiting mahalanobis distance for transformer-based out-of-domain detection","volume":"vol. 35","author":"Podolskiy","year":"2021"},{"key":"10.1016\/j.eswa.2026.132191_bib0036","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.132191_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10428","article-title":"Designing network design spaces","author":"Radosavovic","year":"2020"},{"key":"10.1016\/j.eswa.2026.132191_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.jmva.2019.02.001","article-title":"Integrated rank-weighted depth","volume":"173","author":"Ramsay","year":"2019","journal-title":"Journal of Multivariate Analysis"},{"key":"10.1016\/j.eswa.2026.132191_bib0039","unstructured":"Ren, J., Fort, S., Liu, J., Roy, A. G., Padhy, S., & Lakshminarayanan, B. (2021). A simple fix to mahalanobis distance for improving near-ood detection. arXiv: 2106.09022."},{"key":"10.1016\/j.eswa.2026.132191_bib0040","series-title":"International conference on machine learning","first-page":"8491","article-title":"Detecting out-of-distribution examples with gram matrices","author":"Sastry","year":"2020"},{"key":"10.1016\/j.eswa.2026.132191_sbref0041","series-title":"International conference on learning representations","article-title":"SSD: A unified framework for self-supervised outlier detection","author":"Sehwag","year":"2021"},{"key":"10.1016\/j.eswa.2026.132191_bib0042","series-title":"International conference on machine learning","first-page":"20827","article-title":"Out-of-distribution detection with deep nearest neighbors","author":"Sun","year":"2022"},{"key":"10.1016\/j.eswa.2026.132191_bib0043","unstructured":"Syed, Q., Paulitsch, M., Hagn, K., Cihangir, N. K., Scholl, K.-U., Oboril, F., Hinz, G., & Knoll, A. (2024). Situation monitor: Diversity-driven zero-shot out-of-distribution detection using budding ensemble architecture for object detection. arXiv: 2406.03188."},{"key":"10.1016\/j.eswa.2026.132191_bib0044","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"10.1016\/j.eswa.2026.132191_bib0045","first-page":"11839","article-title":"Csi: Novelty detection via contrastive learning on distributionally shifted instances","volume":"33","author":"Tack","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132191_bib0046","unstructured":"Tajwar, F., Kumar, A., Xie, S. M., & Liang, P. (2021). No true state-of-the-art? OOD detection methods are inconsistent across datasets. arXiv: 2109.05554."},{"key":"10.1016\/j.eswa.2026.132191_bib0047","series-title":"International conference on machine learning","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.eswa.2026.132191_bib0048","series-title":"International conference on machine learning","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","author":"Tan","year":"2021"},{"key":"10.1016\/j.eswa.2026.132191_bib0049","series-title":"European conference on computer vision","first-page":"459","article-title":"Maxvit: Multi-axis vision transformer","author":"Tu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132191_bib0050","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"8769","article-title":"The inaturalist species classification and detection dataset","author":"Van Horn","year":"2018"},{"key":"10.1016\/j.eswa.2026.132191_bib0051","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nature Methods"},{"key":"10.1016\/j.eswa.2026.132191_bib0052","series-title":"Proceedings of SAI intelligent systems conference","first-page":"408","article-title":"Utilizing local outlier factor for open-set classification in high-dimensional data-case study applied for text documents","author":"Walkowiak","year":"2019"},{"key":"10.1016\/j.eswa.2026.132191_bib0053","series-title":"International conference on computational science","first-page":"578","article-title":"Combining outlierness scores and feature extraction techniques for improvement of ood and adversarial attacks detection in DNNS","author":"Walkowiak","year":"2023"},{"key":"10.1016\/j.eswa.2026.132191_bib0054","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4921","article-title":"Vim: Out-of-distribution with virtual-logit matching","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132191_bib0055","series-title":"2010 IEEE computer society conference on computer vision and pattern recognition","first-page":"3485","article-title":"Sun database: Large-scale scene recognition from abbey to zoo","author":"Xiao","year":"2010"},{"key":"10.1016\/j.eswa.2026.132191_bib0056","unstructured":"Yang, J., Wang, P., Zou, D., Zhou, Z., Ding, K., Peng, W., Wang, H., Chen, G., Li, B., Sun, Y. et al. (2022). OpenOOD: Benchmarking generalized out-of-distribution detection. arXiv: 2210.07242."},{"key":"10.1016\/j.eswa.2026.132191_bib0057","doi-asserted-by":"crossref","first-page":"5635","DOI":"10.1007\/s11263-024-02117-4","article-title":"Generalized out-of-distribution detection: A survey","volume":"132","author":"Yang","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132191_bib0058","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., & Wu, Y. (2022). Coca: Contrastive captioners are image-text foundation models. arXiv: 2205.01917."},{"issue":"6","key":"10.1016\/j.eswa.2026.132191_bib0059","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","article-title":"Places: A 10 million image database for scene recognition","volume":"40","author":"Zhou","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132191_bib0060","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"1100","article-title":"Contrastive out-of-distribution detection for pretrained transformers","author":"Zhou","year":"2021"},{"key":"10.1016\/j.eswa.2026.132191_bib0061","doi-asserted-by":"crossref","first-page":"145450","DOI":"10.1109\/ACCESS.2024.3471693","article-title":"Out-of-distribution detection based on multiple metrics fusion of network hidden features","volume":"12","author":"Zhu","year":"2024","journal-title":"IEEE Access"},{"issue":"2","key":"10.1016\/j.eswa.2026.132191_bib0062","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1007\/s11063-022-10970-y","article-title":"Effective out-of-distribution detection in classifier based on PEDCC-loss","volume":"55","author":"Zhu","year":"2023","journal-title":"Neural Processing Letters"},{"issue":"10","key":"10.1016\/j.eswa.2026.132191_bib0063","doi-asserted-by":"crossref","first-page":"4633","DOI":"10.1007\/s11263-024-02099-3","article-title":"Rethinking out-of-distribution detection from a human-centric perspective","volume":"132","author":"Zhu","year":"2024","journal-title":"International Journal of Computer Vision"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011048?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011048?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:01:32Z","timestamp":1780934492000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426011048"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":63,"alternative-id":["S0957417426011048"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132191","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Guidelines for the selection, calibration, and evaluation of post-hoc OOD detectors in high-dimensional representations generated by CNN and ViT models in image recognition","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132191","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"132191"}}