Related papers: SimpleNet: A Simple Network for Image Anomaly Dete…
Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class…
This paper considers image change detection with only a small number of samples, which is a significant problem in terms of a few annotations available. A major impediment of image change detection task is the lack of large annotated…
Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances…
Unsupervised anomaly detection is a daunting task, as it relies solely on normality patterns from the training data to identify unseen anomalies during testing. Recent approaches have focused on leveraging domain-specific transformations or…
Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance. This paper presents a novel SurroundNet…
Anomaly detection and localization in automated industrial manufacturing can significantly enhance production efficiency and product quality. Existing methods are capable of detecting surface defects in pre-defined or controlled imaging…
Anomaly detection in large datasets is essential in astronomy and computer vision. However, due to a scarcity of labelled data, it is often infeasible to apply supervised methods to anomaly detection. We present AnomalyMatch, an anomaly…
In this paper, we introduce a novel task termed unified anomaly detection and classification, which aims to simultaneously detect anomalous regions in images and identify their specific categories. Existing methods typically treat anomaly…
Object detection and instance recognition play a central role in many AI applications like autonomous driving, video surveillance and medical image analysis. However, training object detection models on large scale datasets remains…
While nowadays visual anomaly detection algorithms use deep neural networks to extract salient features from images, the high dimensionality of extracted features makes it difficult to apply those algorithms to large data with 1000s of…
Anomaly detection is a practical and challenging task due to the scarcity of anomaly samples in industrial inspection. Some existing anomaly detection methods address this issue by synthesizing anomalies with noise or external data.…
Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these…
With the rapid advancement of generative models, the visual quality of generated images has become nearly indistinguishable from the real ones, posing challenges to content authenticity verification. Existing methods for detecting…
Anomaly detection (AD) in images, identifying significant deviations from normality, is a critical issue in computer vision. This paper introduces a novel approach to dimensionality reduction for AD using pre-trained convolutional neural…
Graph-level anomaly detection aims to identify abnormal graphs that exhibit deviant structures and node attributes compared to the majority in a graph set. One primary challenge is to learn normal patterns manifested in both fine-grained…
We propose a novel transformer-style architecture called Global-Local Filter Network (GLFNet) for medical image segmentation and demonstrate its state-of-the-art performance. We replace the self-attention mechanism with a combination of…
Anomaly detection in data analysis is an interesting but still challenging research topic in real world applications. As the complexity of data dimension increases, it requires to understand the semantic contexts in its description for…
Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…
Deep generative networks trained via maximum likelihood on a natural image dataset like CIFAR10 often assign high likelihoods to images from datasets with different objects (e.g., SVHN). We refine previous investigations of this failure at…
Anomaly generation is an effective way to mitigate data scarcity for anomaly detection task. Most existing works shine at industrial anomaly generation with multiple specialists or large generative models, rarely generalizing to anomalies…