Discrepancy Scaling for Fast Unsupervised Anomaly Localization

Juha Mylläri; Jukka K Nurminen

doi:10.1109/COMPSAC57700.2023.00042

Discrepancy Scaling for Fast Unsupervised Anomaly Localization

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

Abstrakti

Computer vision systems can automatically find and segment anomalies in images even without ever seeing anomalous observations during training. Many methods for such unsupervised anomaly detection (AD) and localization (AL) tasks have been introduced in recent years, but the most accurate methods tend to be computationally heavy. In this paper, we propose Discrepancy Scaling, a method that significantly improves the accuracy of a very fast AD and AL approach called Student-Teacher Feature Pyramid Matching. We show that with Discrepancy Scaling, even a small, mobile-friendly convolutional neural network can perform well on AD and AL tasks.

Alkuperäiskieli	englanti
Otsikko	2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)
Sivumäärä	6
Kustantaja	IEEE
Julkaisupäivä	elok. 2023
Sivut	274-279
ISBN (elektroninen)	979-8-3503-2697-0
DOI - pysyväislinkit	https://doi.org/10.1109/COMPSAC57700.2023.00042
Tila	Julkaistu - elok. 2023
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	Annual Computers, Software, and Applications Conference - Torino, Italia Kesto: 26 kesäk. 2023 → 30 kesäk. 2023 Konferenssinumero: 47

Tieteenalat

113 Tietojenkäsittely- ja informaatiotieteet

Pääsy asiakirjaan

10.1109/COMPSAC57700.2023.00042

Discrepancy_Scaling_acceptedHyväksytty kirjoittajan käsikirjoitus, 1,43 MBLisenssi: Määrittelemätön

IML4E: Industrial Machine Learning for Enterprises
Nurminen, J. K. (Projektinjohtaja), Hu, R. Y. (osallistuja), Hussain, Z. (osallistuja), Kemell, K.-K. (osallistuja), Kivimäki, J. I. (osallistuja), Laisi, J. S. (osallistuja), Lehtonen, A. I. (osallistuja), Luo, Y. (osallistuja), Lwakatare, L. E. M. (osallistuja), Muiruri, D. (osallistuja), Myllyaho, L. (osallistuja), Mylläri, J. (osallistuja), Mylläri, J. (osallistuja), Raatikainen, M. (osallistuja), Rantanen, R. J. (osallistuja), Rensing, F. (osallistuja), Salmenperä, I. E. (osallistuja), Samarasekara, H. (osallistuja), Siilasjoki, N. J. (osallistuja), Vidanapathirana, J. C. (osallistuja), Myllyaho, L. (Osallistuja) & Raatikainen, M. (Osallistuja)
Innovaatiorahoituskeskus Business Finland
01/05/2021 → 28/02/2025
Projekti: Business Finland
IVVES: IVVES
Mikkonen, T. (Projektinjohtaja), Nurminen, J. K. (Projektinjohtaja), Becker, L. V. A. (osallistuja), Hussain, Z. (osallistuja), Kauhanen, E. O. (osallistuja), Kramar, V. T. (osallistuja), Laanti, T. M. (osallistuja), Muiruri, D. (osallistuja), Myllyaho, L. (osallistuja), Mylläri, J. (osallistuja), Raatikainen, M. (osallistuja), Salmenperä, I. E. (osallistuja), Valjakka, J. H. (osallistuja), Hussain, Z. (Osallistuja), Myllyaho, L. (Osallistuja) & Raatikainen, M. (Osallistuja)
Business Finland Oy
01/01/2020 → 31/03/2024
Projekti: Business Finland

Siteeraa tätä

@inproceedings{166530a21d4e4e02a96c6a2b8276e752,

title = "Discrepancy Scaling for Fast Unsupervised Anomaly Localization",

abstract = "Computer vision systems can automatically find and segment anomalies in images even without ever seeing anomalous observations during training. Many methods for such unsupervised anomaly detection (AD) and localization (AL) tasks have been introduced in recent years, but the most accurate methods tend to be computationally heavy. In this paper, we propose Discrepancy Scaling, a method that significantly improves the accuracy of a very fast AD and AL approach called Student-Teacher Feature Pyramid Matching. We show that with Discrepancy Scaling, even a small, mobile-friendly convolutional neural network can perform well on AD and AL tasks.",

keywords = "113 Computer and information sciences, Anomaly detection, Anomaly localization, Deep learning, Unsupervised learning",

author = "Juha Myll{\"a}ri and Nurminen, {Jukka K}",

year = "2023",

month = aug,

doi = "10.1109/COMPSAC57700.2023.00042",

language = "English",

pages = "274--279",

booktitle = "2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)",

publisher = "IEEE",

address = "United States",

note = "Annual Computers, Software, and Applications Conference, COMPSAC ; Conference date: 26-06-2023 Through 30-06-2023",

}

TY - GEN

T1 - Discrepancy Scaling for Fast Unsupervised Anomaly Localization

AU - Mylläri, Juha

AU - Nurminen, Jukka K

N1 - Conference code: 47

PY - 2023/8

Y1 - 2023/8

N2 - Computer vision systems can automatically find and segment anomalies in images even without ever seeing anomalous observations during training. Many methods for such unsupervised anomaly detection (AD) and localization (AL) tasks have been introduced in recent years, but the most accurate methods tend to be computationally heavy. In this paper, we propose Discrepancy Scaling, a method that significantly improves the accuracy of a very fast AD and AL approach called Student-Teacher Feature Pyramid Matching. We show that with Discrepancy Scaling, even a small, mobile-friendly convolutional neural network can perform well on AD and AL tasks.

AB - Computer vision systems can automatically find and segment anomalies in images even without ever seeing anomalous observations during training. Many methods for such unsupervised anomaly detection (AD) and localization (AL) tasks have been introduced in recent years, but the most accurate methods tend to be computationally heavy. In this paper, we propose Discrepancy Scaling, a method that significantly improves the accuracy of a very fast AD and AL approach called Student-Teacher Feature Pyramid Matching. We show that with Discrepancy Scaling, even a small, mobile-friendly convolutional neural network can perform well on AD and AL tasks.

KW - 113 Computer and information sciences

KW - Anomaly detection

KW - Anomaly localization

KW - Deep learning

KW - Unsupervised learning

U2 - 10.1109/COMPSAC57700.2023.00042

DO - 10.1109/COMPSAC57700.2023.00042

M3 - Conference contribution

SP - 274

EP - 279

BT - 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)

PB - IEEE

T2 - Annual Computers, Software, and Applications Conference

Y2 - 26 June 2023 through 30 June 2023

ER -

Discrepancy Scaling for Fast Unsupervised Anomaly Localization

Abstrakti

Tieteenalat

Pääsy asiakirjaan

Projektit

IML4E: Industrial Machine Learning for Enterprises

IVVES: IVVES

Siteeraa tätä