{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:27:32Z","timestamp":1770917252672,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191711","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-7","source":"Crossref","is-referenced-by-count":5,"title":["Out-of-Distribution Detection in Deep Learning Models: A Feature Space-Based Approach"],"prefix":"10.1109","author":[{"given":"Thiago Medeiros","family":"Carvalho","sequence":"first","affiliation":[{"name":"Pontifical Catholic University of Rio de Janeiro,Department of Electrical Engineering,Rio de Janeiro,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marley","family":"Vellasco","sequence":"additional","affiliation":[{"name":"Pontifical Catholic University of Rio de Janeiro,Department of Electrical Engineering,Rio de Janeiro,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 Franco","family":"Amaral","sequence":"additional","affiliation":[{"name":"Rio de Janeiro State University,Department of Electronics and Telecommunications Engineering,Rio de Janeiro,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"387","article-title":"Anomaly detection in image datasets using convolutional neural networks, center loss, and maha- lanobis distance","author":"vareldzhan","year":"0","journal-title":"2021 Ural Symposium on Biomedical Engineering Radioelectronics and Information Technology (USBEREIT)"},{"key":"ref12","article-title":"Enhancing the reliability of out-of- distribution image detection in neural networks","author":"liang","year":"0","journal-title":"6th International Conference on Learning Representations ICLR 2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/02522667.2022.2037283"},{"key":"ref14","first-page":"677","article-title":"On the importance of gradients for detecting distributional shifts in the wild","volume":"34","author":"huang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref30","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","volume":"abs 1910 1108","author":"sanh","year":"2019","journal-title":"ArXiv"},{"key":"ref11","first-page":"21 464","article-title":"Energy-based out-of-distribution detection","volume":"33","author":"liu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"23 631","article-title":"Mitigating neural network overconfidence with logit normalization","author":"wei","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.244"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330656"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3533378"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3113828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897694"},{"key":"ref19","article-title":"Why is the mahalanobis distance effective for anomaly detection?","author":"kamoi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Openood: Benchmarking generalized out-of-distribution detection","author":"yang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00860"},{"key":"ref23","author":"netzer","year":"2011","journal-title":"Reading digits in natural images with unsupervised feature learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1007\/978-3-319-46478-7_31","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"2016","journal-title":"Computer Vision-ECCV 2016 14th European Conference"},{"key":"ref20","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1404"},{"key":"ref21","article-title":"Character-level convolutional networks for text classification","volume":"28","author":"zhang","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"maas","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref27","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"0","journal-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref29","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Revisiting softmax for uncertainty approximation in text classification","author":"holm","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3175195"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"ref4","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref3","first-page":"2041","article-title":"Breaking down out-of-distribution detection: Many methods based on ood training data estimate a combination of the same core quantities","author":"bitterwolf","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06027-1"},{"key":"ref5","article-title":"A unified survey on anomaly, novelty, open-set, and out-of-distribution detection: Solutions and future challenges","author":"salehi","year":"2021","journal-title":"ArXiv Preprint"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","location":"Gold Coast, Australia","start":{"date-parts":[[2023,6,18]]},"end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191711.pdf?arnumber=10191711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:47:29Z","timestamp":1692640049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191711","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}