Quantum Patch-Based Autoencoder for Anomaly Segmentation
Quantum Machine Learning investigates the pos-sibility of quantum computers enhancing Machine Learning algorithms. Anomaly segmentation is a fundamental task in various domains to identify irregularities at sample level and can be addressed with both supervised and unsupervised methods. Autoencoders...
Uloženo v:
| Vydáno v: | 2024 IEEE International Conference on Quantum Computing and Engineering (QCE) Ročník 1; s. 259 - 267 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
15.09.2024
|
| Témata: | |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Quantum Machine Learning investigates the pos-sibility of quantum computers enhancing Machine Learning algorithms. Anomaly segmentation is a fundamental task in various domains to identify irregularities at sample level and can be addressed with both supervised and unsupervised methods. Autoencoders are commonly used in unsupervised tasks, where models are trained to reconstruct normal instances efficiently, al-lowing anomaly identification through high reconstruction errors. While quantum autoencoders have been proposed in the literature, their application to anomaly segmentation tasks remains unexplored. In this paper, we introduce a patch-based quantum autoencoder (QPB-AE) for image anomaly segmentation, with a number of parameters scaling logarithmically with patch size. QPB-AE reconstructs the quantum state of the embedded input patches, computing an anomaly map directly from measurement through a SWAP test without reconstructing the input image. We evaluate its performance across multiple datasets and parameter configurations and compare it against a classical counterpart. |
|---|---|
| AbstractList | Quantum Machine Learning investigates the pos-sibility of quantum computers enhancing Machine Learning algorithms. Anomaly segmentation is a fundamental task in various domains to identify irregularities at sample level and can be addressed with both supervised and unsupervised methods. Autoencoders are commonly used in unsupervised tasks, where models are trained to reconstruct normal instances efficiently, al-lowing anomaly identification through high reconstruction errors. While quantum autoencoders have been proposed in the literature, their application to anomaly segmentation tasks remains unexplored. In this paper, we introduce a patch-based quantum autoencoder (QPB-AE) for image anomaly segmentation, with a number of parameters scaling logarithmically with patch size. QPB-AE reconstructs the quantum state of the embedded input patches, computing an anomaly map directly from measurement through a SWAP test without reconstructing the input image. We evaluate its performance across multiple datasets and parameter configurations and compare it against a classical counterpart. |
| Author | Poggiali, Alessandro Madeira, Maria Francisca Lorenz, Jeanette Miriam |
| Author_xml | – sequence: 1 givenname: Maria Francisca surname: Madeira fullname: Madeira, Maria Francisca email: francisca.madeira@lmu.de organization: Ludwig-Maximilians-Universität München, Fraunhofer IKS,Munich,Germany – sequence: 2 givenname: Alessandro surname: Poggiali fullname: Poggiali, Alessandro email: alessandro.poggiali@phd.unipi.it organization: University of Pisa, Fraunhofer IKS,Munich,Germany – sequence: 3 givenname: Jeanette Miriam surname: Lorenz fullname: Lorenz, Jeanette Miriam email: jeanette.miriam.lorenz@iks.fraunhofer.de organization: Ludwig-Maximilians-Universität München, Fraunhofer IKS,Munich,Germany |
| BookMark | eNotzE1OwzAQQGEjwQJKTwALXyBh7HETexmi8iNVggpYV1N7DJEaG6XOorcHCVZv8-ldifOUEwtxo6BWCtzdtl83oO2q1qBNDQDozsTStc4iqpVR2NpLYbczpTKP8pWK_6ru6chBdnPJnHwOPMmYJ9mlPNLhJN_4c-RUqAw5XYuLSIcjL_-7EB8P6_f-qdq8PD733aYaVNuUKiodIWhqMSprjW-9c8ZZUtojN0wO9po5RmsAf6EJATnsDZnYeAZNuBC3f9-BmXff0zDSdNopsFoZRPwB_m5E7g |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/QCE60285.2024.00039 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9798331541378 |
| EndPage | 267 |
| ExternalDocumentID | 10821433 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IL CBEJK RIE RIL |
| ID | FETCH-LOGICAL-i176t-f12f0d2a73f1884c7c99498a12c3e6ea90b2eeff8403f0d4dd3edb4a4f6ce02a3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001438831500029&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Jan 15 06:21:19 EST 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i176t-f12f0d2a73f1884c7c99498a12c3e6ea90b2eeff8403f0d4dd3edb4a4f6ce02a3 |
| PageCount | 9 |
| ParticipantIDs | ieee_primary_10821433 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-Sept.-15 |
| PublicationDateYYYYMMDD | 2024-09-15 |
| PublicationDate_xml | – month: 09 year: 2024 text: 2024-Sept.-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | 2024 IEEE International Conference on Quantum Computing and Engineering (QCE) |
| PublicationTitleAbbrev | QCE |
| PublicationYear | 2024 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 1.8827859 |
| Snippet | Quantum Machine Learning investigates the pos-sibility of quantum computers enhancing Machine Learning algorithms. Anomaly segmentation is a fundamental task... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 259 |
| SubjectTerms | Anomaly Segmen-tation Autoencoders Computational modeling Data models Image reconstruction Image segmentation Location awareness Noise Quantum Autoencoder Quantum computing Quantum Machine Learning Scalability Training |
| Title | Quantum Patch-Based Autoencoder for Anomaly Segmentation |
| URI | https://ieeexplore.ieee.org/document/10821433 |
| Volume | 1 |
| WOSCitedRecordID | wos001438831500029&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA62ePCkYsU3OXiN5rWb5KilxYOUFhV6K9lkogW7lXZX8N-bbNfHxYO3EAJhJiTfTJLvG4QuZZCZKJyPkRvVREpriHFZID63PAsaqAmNzuy9Go30dGrGLVm94cIAQPP5DK5Ss3nL90tXp6uyuMM1j_guOqijlNqQtVolIUbN9aQ_yCNcZjHr40kTm6YK4L9qpjSQMdz952R7qPdDvsPjb1jZR1tQHiA9qaML6gUex6PzhdxG7PH4pq6WSYfSwwrH2BPHVH5hXz_wAzwvWkpR2UNPw8Fj_460RQ_InKm8IoHxQD23SgSmtXTKGSONtow7ATlYQwsOEEJMzEQcKL0X4AtpZcgdUG7FIeqWyxKOENYBTFoHmlsjtQyaCcU8s1YVPNPGHqNeMnv2ttG1mH1ZfPJH_ynaSZ5NvyVYdoa61aqGc7Tt3qv5enXRrMYnsUONhw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBT2pWPFtDl5X89rd5KilpWItLVborWSTiRbardRdwX9vsl0fFw_eQgiEmZB8M0m-bxC6FE7EPDPWR25ERkJoFSkTu8gmmsVOAlGu0pntpf2-HI_VoCarV1wYAKg-n8FVaFZv-XZhynBV5ne4ZB7f-TraiIVgdEXXqrWEKFHXw1Y78YAZ-7yPBVVsEmqA_6qaUoFGZ-ef0-2i5g_9Dg--gWUPrUG-j-Sw9E4o53jgD8-X6Najj8U3ZbEISpQWlthHn9gn83M9-8CP8DyvSUV5Ez112qNWN6rLHkRTmiZF5ChzxDKdckelFCY1SgklNWWGQwJakYwBOOdTM-4HCms52Exo4RIDhGl-gBr5IodDhKUDFVaCJFoJKZykPKWWap1mLJZKH6FmMHvyulK2mHxZfPxH_wXa6o4eepPeXf_-BG0HL4e_EzQ-RY1iWcIZ2jTvxfRteV6tzCc-65DO |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2024+IEEE+International+Conference+on+Quantum+Computing+and+Engineering+%28QCE%29&rft.atitle=Quantum+Patch-Based+Autoencoder+for+Anomaly+Segmentation&rft.au=Madeira%2C+Maria+Francisca&rft.au=Poggiali%2C+Alessandro&rft.au=Lorenz%2C+Jeanette+Miriam&rft.date=2024-09-15&rft.pub=IEEE&rft.volume=1&rft.spage=259&rft.epage=267&rft_id=info:doi/10.1109%2FQCE60285.2024.00039&rft.externalDocID=10821433 |