Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Jie, Wu, Yao, Luo, Xiaotong, Wu, Zongze
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.05645
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916289591640064
author Liu, Jie
Wu, Yao
Luo, Xiaotong
Wu, Zongze
author_facet Liu, Jie
Wu, Yao
Luo, Xiaotong
Wu, Zongze
contents In industrial scenarios, it is crucial not only to identify anomalous items but also to classify the type of anomaly. However, research on anomaly multi-classification remains largely unexplored. This paper proposes a novel and valuable research task called anomaly multi-classification. Given the challenges in applying few-shot learning to this task, due to limited training data and unique characteristics of anomaly images, we introduce a baseline model that combines RelationNet and PatchCore. We propose a data generation method that creates pseudo classes and a corresponding proxy task, aiming to bridge the gap in transferring few-shot learning to industrial scenarios. Furthermore, we utilize contrastive learning to improve the vanilla baseline, achieving much better performance than directly fine-tune a ResNet. Experiments conducted on MvTec AD and MvTec3D AD demonstrate that our approach shows superior performance in this novel task.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05645
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Anomaly Multi-classification in Industrial Scenarios: Transferring Few-shot Learning to a New Task
Liu, Jie
Wu, Yao
Luo, Xiaotong
Wu, Zongze
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
In industrial scenarios, it is crucial not only to identify anomalous items but also to classify the type of anomaly. However, research on anomaly multi-classification remains largely unexplored. This paper proposes a novel and valuable research task called anomaly multi-classification. Given the challenges in applying few-shot learning to this task, due to limited training data and unique characteristics of anomaly images, we introduce a baseline model that combines RelationNet and PatchCore. We propose a data generation method that creates pseudo classes and a corresponding proxy task, aiming to bridge the gap in transferring few-shot learning to industrial scenarios. Furthermore, we utilize contrastive learning to improve the vanilla baseline, achieving much better performance than directly fine-tune a ResNet. Experiments conducted on MvTec AD and MvTec3D AD demonstrate that our approach shows superior performance in this novel task.
title Anomaly Multi-classification in Industrial Scenarios: Transferring Few-shot Learning to a New Task
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2406.05645