PGTNET: PROTOTYPE GUIDED TRANSFER NETWORK FOR FEW-SHOT ANOMALY LOCALIZATION

  • Zisong Zhuang
  • , Junhang Zhang
  • , Luwei Xiao
  • , Tianlong Ma*
  • , Liang He*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Anomaly localization is pixel-level regions detection in the image. The challenge is how to generate accurate representations of the novel anomaly types which are multifarious. Besides, the anomaly sample size is often not enough to support model learning to detection because of the limitations of real conditions. In this work, we present a novel few-shot setting for anomaly detection and reorganize the defective datasets. Based on the few-shot learning, we transfer the idea of metric learning and propose the prototype-guided transfer network (PGTNet). Extensive experiment results suggest that PGTNet outperforms current SOTA methods and provides a novel perspective for the anomaly localization task.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PublisherIEEE Computer Society
Pages2321-2325
Number of pages5
ISBN (Electronic)9781665496209
DOIs
StatePublished - 2022
Event29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France
Duration: 16 Oct 202219 Oct 2022

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference29th IEEE International Conference on Image Processing, ICIP 2022
Country/TerritoryFrance
CityBordeaux
Period16/10/2219/10/22

Keywords

  • Anomaly Detection
  • Few-Shot Learning
  • Metric Learning

Fingerprint

Dive into the research topics of 'PGTNET: PROTOTYPE GUIDED TRANSFER NETWORK FOR FEW-SHOT ANOMALY LOCALIZATION'. Together they form a unique fingerprint.

Cite this