Related papers: Hierarchical Gaussian Mixture Normalizing Flow Mod…
Anomaly detection (AD) plays an important role in various real-world applications. Recent advancements in AD, however, are often biased towards industrial inspection, struggle to generalize to broader tasks like semantic anomaly detection…
Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i.e., healthy) images to detect any abnormal (i.e., unhealthy) samples that do not conform to the expected normal patterns. UAD has two main…
While the mainstream research in anomaly detection has mainly followed the one-class classification, practical industrial environments often incur noisy training data due to annotation errors or lack of labels for new or refurbished…
One-class anomaly detection aims to detect objects that do not belong to a predefined normal class. In practice training data lack those anomalous samples; hence state-of-the-art methods are trained to discriminate between normal and…
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…
We propose Flow Mismatching, an unsupervised anomaly detection method that deliberately avoids reconstruction-based paradigms. Instead, we treat flow matching as geometric dynamics and leverage a key insight: anomalies occur at places where…
This paper explores the problem of class-generalizable anomaly detection, where the objective is to train one unified AD model that can generalize to detect anomalies in diverse classes from different domains without any retraining or…
Anomaly detection from graph data has drawn much attention due to its practical significance in many critical applications including cybersecurity, finance, and social networks. Existing data mining and machine learning methods are either…
Graph-level anomaly detection (GLAD) has already gained significant importance and has become a popular field of study, attracting considerable attention across numerous downstream works. The core focus of this domain is to capture and…
Graph anomaly detection (GAD), which aims to identify nodes in a graph that significantly deviate from normal patterns, plays a crucial role in broad application domains. However, existing GAD methods are one-model-for-one-dataset…
This study presents an adversarial method for anomaly detection in real-world applications, leveraging the power of generative adversarial neural networks (GANs) through cycle consistency in reconstruction error. Previous methods suffer…
Current anomaly detection methods primarily focus on low-resolution scenarios. For high-resolution images, conventional downsampling often results in missed detections of subtle anomalous regions due to the loss of fine-grained…
Graph anomaly detection (GAD) is critical for identifying abnormal nodes in graph-structured data from diverse domains, including cybersecurity and social networks. The existing GAD methods often focus on the learning paradigms of…
Graph Anomaly Detection (GAD) in heterogeneous networks presents unique challenges due to node and edge heterogeneity. Existing Graph Neural Network (GNN) methods primarily focus on homogeneous GAD and thus fail to address three key issues:…
Anomaly Detection (AD) in images is a fundamental computer vision problem and refers to identifying images and image substructures that deviate significantly from the norm. Popular AD algorithms commonly try to learn a model of normality…
High-resolution point clouds~(HRPCD) anomaly detection~(AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the…
With the rapid growth of graph-structured data in critical domains, unsupervised graph-level anomaly detection (UGAD) has become a pivotal task. UGAD seeks to identify entire graphs that deviate from normal behavioral patterns. However,…
Graph anomaly detection aims to identify irregular patterns in graph-structured data. Most unsupervised GNN-based methods rely on the homophily assumption that connected nodes share similar attributes. However, real-world graphs often…
Anomaly detection is fundamental yet, challenging problem with practical applications in industry. The current approaches neglect the higher-order dependencies within the networks of interconnected sensors in the high-dimensional time…
We present a novel end-to-end partially supervised deep learning approach for video anomaly detection and localization using only normal samples. The insight that motivates this study is that the normal samples can be associated with at…