{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T06:27:52Z","timestamp":1761719272879,"version":"3.28.0"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"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":[[2023,12,15]]},"DOI":"10.1109\/bigdata59044.2023.10386202","type":"proceedings-article","created":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T18:28:47Z","timestamp":1705948127000},"page":"1047-1051","source":"Crossref","is-referenced-by-count":1,"title":["Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunities"],"prefix":"10.1109","author":[{"given":"Leman","family":"Akoglu","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Heinz College of Information Systems and Public Policy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaemin","family":"Yoo","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A cookbook of self-supervised learning","author":"Balestriero","year":"2023","journal-title":"arXiv preprint arXiv:2304.12210"},{"volume-title":"Self-supervised learning: The dark matter of intelligence","year":"2021","author":"LeCun","key":"ref2"},{"volume-title":"Self-supervised learning: The plan to make deep learning data-efficient","year":"2020","author":"Dickson","key":"ref3"},{"volume-title":"Gpt-4 technical report","year":"2023","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10742-016-0154-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDIS.2018.00043"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.05.042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3131584"},{"key":"ref10","article-title":"Calibrated one-class classification for unsupervised time series anomaly detection","author":"Xu","year":"2022","journal-title":"arXiv preprint arXiv:2207.12201"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/b:mach.0000008084.60811.49"},{"key":"ref12","first-page":"4393","article-title":"Deep one-class classification","author":"Ruff","year":"2018","journal-title":"ICML"},{"key":"ref13","article-title":"Deep anomaly detection using geometric transformations","author":"Golan","year":"2018","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref15","article-title":"Deep anomaly detection with outlier exposure","author":"Hendrycks","year":"2019","journal-title":"ICLR"},{"key":"ref16","article-title":"Exposing outlier exposure: What can be learned from few, one, and zero outlier images","author":"Liznerski","year":"2022","journal-title":"arXiv:2205.11474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1117\/12.487069"},{"issue":"2","key":"ref18","article-title":"A classification framework for anomaly detection","volume":"6","author":"Steinwart","year":"2005","journal-title":"JMLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150459"},{"key":"ref20","article-title":"Data augmentation is a hyperparameter: Cherry-picked self-supervision for unsupervised anomaly detection is creating the illusion of success","author":"Yoo","year":"2023","journal-title":"TMLR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/456"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref23","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"NeruIPS"},{"key":"ref24","article-title":"High fidelity visualization of what your self-supervised representation knows about","author":"Bordes","year":"2022","journal-title":"TMLR"},{"key":"ref25","first-page":"3252","article-title":"The SSL interplay: Augmentations, inductive bias, and generalization","author":"Cabannes","year":"2023","journal-title":"ICML"},{"key":"ref26","first-page":"26671","article-title":"Contrastive and non-contrastive self-supervised learning recover global and local spectral embedding methods","volume":"35","author":"Balestriero","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref28","article-title":"Self-tuning networks: Bilevel optimization of hyperparameters using structured best-response functions","author":"MacKay","year":"2019","journal-title":"arXiv:1903.03088"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-022-01555-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4120"},{"key":"ref33","first-page":"9603","article-title":"Hyperparameter sensitivity in deep outlier detection: Analysis and a scalable hyper-ensemble solution","volume":"35","author":"Ding","year":"2022","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098052"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_39"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3606274.3606277"},{"key":"ref37","first-page":"4489","article-title":"Automatic unsupervised outlier model selection","author":"Zhao","year":"2021","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00088"},{"key":"ref39","article-title":"Towards unsupervised hpo for outlier detection","author":"Zhao","year":"2022","journal-title":"arXiv preprint arXiv:2208.11727"},{"key":"ref40","article-title":"Fast unsupervised model tuning with hypernetworks for deep outlier detection","author":"Zhao","year":"2023","journal-title":"arXiv:2307.10529"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2791347.2791352"},{"key":"ref42","article-title":"How to evaluate the quality of unsupervised anomaly detection algorithms?","volume":"abs\/1607.01152","author":"Goix","year":"2016","journal-title":"CoRR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15625\/1813-9663\/32\/3\/8455"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-24025-8"},{"key":"ref45","article-title":"Test accuracy vs. generalization gap: Model selection in NLP w\/out training or testing data","author":"Yang","year":"2023","journal-title":"KDD"},{"key":"ref46","first-page":"6127","article-title":"InfoGAN-CR and ModelCentrality: Self-supervised model training and selection for disentangling GANs","author":"Lin","year":"2020","journal-title":"ICML"},{"key":"ref47","article-title":"Unsupervised model selection for variational disentangled representation learning","author":"Duan","year":"2020","journal-title":"ICLR. OpenReview.net"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43412-9_15"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-34239-7"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1484"},{"key":"ref52","article-title":"End-to-end augmentation tuning for self-supervised anomaly detection","author":"Yoo","year":"2023","journal-title":"arXiv:2306.12033"},{"key":"ref53","article-title":"A complete survey on generative ai: Is chatgpt from gpt-4 to gpt-5 all you need?","author":"Zhang","year":"2023","journal-title":"arXiv:2303.11717"},{"key":"ref54","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2015.79"}],"event":{"name":"2023 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2023,12,15]]},"location":"Sorrento, Italy","end":{"date-parts":[[2023,12,18]]}},"container-title":["2023 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10385234\/10386078\/10386202.pdf?arnumber=10386202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T01:44:22Z","timestamp":1706751862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10386202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/bigdata59044.2023.10386202","relation":{},"subject":[],"published":{"date-parts":[[2023,12,15]]}}}