Learning Unsupervised Metaformer for Anomaly Detection
Anomaly detection (AD) aims to address the task of classification or localization of image anomalies. This paper addresses two pivotal issues of reconstruction-based approaches to AD in images, namely, model adaptation and reconstruction gap. The former generalizes an AD model to tackling a broad range of object categories, while the latter provides useful clues for localizing abnormal regions. At the core of our method is an unsupervised universal model, termed as Metaformer, which leverages both meta-learned model parameters to achieve high model adaptation capability and instance-aware attention to emphasize the focal regions for localizing abnormal regions, i.e., to explore the reconstruction gap at those regions of interest. We justify the effectiveness of our method with SOTA results on the MVTec AD dataset of industrial images and highlight the adaptation flexibility of the universal Metaformer with multi-class and few-shot scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionSimilar Papers 제목 키워드 기반
UaiNets: From Unsupervised to Active Deep Anomaly Detection
This work presents a method for active anomaly detection which can be built upon existing deep learning solutions for unsupervised anomaly detection. We show that a prior needs to be assumed on what the anomalies are, in…
Anomaly DetectionDeep LearningUnsupervised Anomaly DetectionMetaFormer Baselines for Vision
MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capacity of MetaFormer, again, without focusin…
Domain GeneralizationImage ClassificationMetaFormer: A Unified Meta Framework for Fine-Grained Recognition
Fine-Grained Visual Classification(FGVC) is the task that requires recognizing the objects belonging to multiple subordinate categories of a super-category. Recent state-of-the-art methods usually design sophisticated le…
AttributeFine-Grained Image ClassificationImage ClassificationUMAD: Unsupervised Mask-Level Anomaly Detection for Autonomous Driving
Dealing with atypical traffic scenarios remains a challenging task in autonomous driving. However, most anomaly detection approaches cannot be trained on raw sensor data but require exposure to outlier data and powerful …
Anomaly DetectionAutonomous DrivingImage SegmentationSegmentation+3Anomaly Detection with Inexact Labels
We propose a supervised anomaly detection method for data with inexact anomaly labels, where each label, which is assigned to a set of instances, indicates that at least one instance in the set is anomalous. Although man…
Anomaly DetectionMultiple Instance LearningSupervised Anomaly DetectionUnsupervised Anomaly Detection