Related papers: CNC: Cross-modal Normality Constraint for Unsuperv…

Video anomaly detection is commonly used in many applications such as security surveillance and is very challenging.A majority of recent video anomaly detection approaches utilize deep reconstruction models, but their performance is often…

Anomaly detection is an important task for complex systems (e.g., industrial facilities, manufacturing, large-scale science experiments), where failures in a sub-system can lead to low yield, faulty products, or even damage to components.…

Detecting anomalous activity in video surveillance often involves using only normal activity data in order to learn an accurate detector. Due to lack of annotated data for some specific target domain, one could employ existing data from a…

Anomaly segmentation plays a pivotal role in identifying atypical objects in images, crucial for hazard detection in autonomous driving systems. While existing methods demonstrate noteworthy results on synthetic data, they often fail to…

Open-set domain generalization (OSDG) tackles the dual challenge of recognizing unknown classes while simultaneously striving to generalize across unseen domains without using target data during training. In this article, an OSDG framework…

Deep anomaly detection (AD) aims to provide robust and efficient classifiers for one-class and unbalanced settings. However current AD models still struggle on edge-case normal samples and are often unable to keep high performance over…

In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety and generalize to new domains. However, existing methods often struggle to distinguish between…

Anomaly synthesis is a crucial approach to augment abnormal data for advancing anomaly inspection. Based on the knowledge from the large-scale pre-training, existing text-to-image anomaly synthesis methods predominantly focus on textual…

Graph anomaly detection (GAD) is a challenging binary classification problem due to its different structural distribution between anomalies and normal nodes -- abnormal nodes are a minority, therefore holding high heterophily and low…

Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high…

Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them. In addition, the multi-stage or…

Deployed real-world machine learning applications are often subject to uncontrolled and even potentially malicious inputs. Those out-of-domain inputs can lead to unpredictable outputs and sometimes catastrophic safety issues. Prior studies…

Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting during parameter updates and feature conflicts between tasks.…

Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection. The exceptional image reconstruction capabilities of recently popular diffusion models have sparked research efforts to utilize them for enhanced…

This work studies a challenging and practical issue known as multi-class unsupervised anomaly detection (MUAD). This problem requires only normal images for training while simultaneously testing both normal and anomaly images across…

Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomaly detection. This paper explores the potential of…

Visual anomaly detection in real-world industrial settings faces two major limitations. First, most existing methods are trained on purely normal data or on unlabeled datasets assumed to be predominantly normal, presuming the absence of…

Video anomaly detection is a challenging task because of diverse abnormal events. To this task, methods based on reconstruction and prediction are wildly used in recent works, which are built on the assumption that learning on normal data,…

Daily operation of a large-scale experiment is a resource consuming task, particularly from perspectives of routine data quality monitoring. Typically, data comes from different sub-detectors and the global quality of data depends on the…

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…