Results 11 to 20 of about 5,452,269 (307)
SA-PatchCore: Anomaly Detection in Dataset With Co-Occurrence Relationships Using Self-Attention
IEEE Access, 2023 Various unsupervised anomaly detection methods using deep learning have recently been proposed, and the accuracy of the anomaly detection technique for local anomalies has been improved.
Kengo Ishida +5 more
doaj +1 more source
Saliencycut: Augmenting Plausible Anomalies for Anomaly Detection
Pattern Recognition, 2023 Anomaly detection under open-set scenario is a challenging task that requires learning discriminative fine-grained features to detect anomalies that were even unseen during training. As a cheap yet effective approach, data augmentation has been widely used to create pseudo anomalies for better training of such models.
Jianan Ye +5 more
openaire +2 more sources
DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection [PDF]
IEEE International Conference on Computer Vision, 2021 Visual surface anomaly detection aims to detect local image regions that significantly deviate from normal appearance. Recent surface anomaly detection methods rely on generative models to accurately reconstruct the normal areas and to fail on anomalies.
Vitjan Zavrtanik, M. Kristan, D. Skočaj
semanticscholar +1 more source
SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation [PDF]
European Conference on Computer Vision, 2022 Visual anomaly detection is commonly used in industrial quality inspection. In this paper, we present a new dataset as well as a new self-supervised learning method for ImageNet pre-training to improve anomaly detection and segmentation in 1-class and 2 ...
Yang Zou +4 more
semanticscholar +1 more source
A Unified Model for Multi-class Anomaly Detection [PDF]
Neural Information Processing Systems, 2022 Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects. In this work, we present UniAD that accomplishes anomaly detection for multiple classes with a unified framework.
Zhiyuan You +6 more
semanticscholar +1 more source
Nuclear Physics B, 2022 Anomaly detection algorithms have been proved to be useful in the search of new physics beyond the Standard Model. However, a prerequisite for using an anomaly detection algorithm is that the signal to be sought is indeed anomalous.
Ji-Chong Yang, Yu-Chen Guo, Li-Hua Cai
doaj +1 more source
Rethinking Graph Neural Networks for Anomaly Detection [PDF]
International Conference on Machine Learning, 2022 Graph Neural Networks (GNNs) are widely applied for graph anomaly detection. As one of the key components for GNN design is to select a tailored spectral filter, we take the first step towards analyzing anomalies via the lens of the graph spectrum.
Jianheng Tang +3 more
semanticscholar +1 more source
ADBench: Anomaly Detection Benchmark [PDF]
Neural Information Processing Systems, 2022 Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data?
Songqiao Han +4 more
semanticscholar +1 more source
DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection [PDF]
Computer Vision and Pattern Recognition, 2022 Visual anomaly detection, an important problem in computer vision, is usually formulated as a one-class classification and segmentation task. The student-teacher (S- T) framework has proved to be effective in solving this chal-lenge.
Xuan Zhang +5 more
semanticscholar +1 more source
Predictive anomaly detection for marine diesel engine based on echo state network and autoencoder
Energy Reports, 2022 Marine diesel engine with high thermal efficiency and good economy has become the main power of ships. Anomaly detection is an important method to improve the operation reliability of marine diesel engine.
Chong Qu +3 more
doaj +1 more source