Related papers: CRADL: Contrastive Representations for Unsupervise…

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…

The essence of unsupervised anomaly detection is to learn the compact distribution of normal samples and detect outliers as anomalies in testing. Meanwhile, the anomalies in real-world are usually subtle and fine-grained in a…

Contrastive learning, which aims to capture general representation from unlabeled images to initialize the medical analysis models, has been proven effective in alleviating the high demand for expensive annotations. Current methods mainly…

Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting…

Anomaly detection in medical imaging is to distinguish the relevant biomarkers of diseases from those of normal tissues. Deep supervised learning methods have shown potentials in various detection tasks, but its performances would be…

Graph anomaly detection aims to identify abnormal patterns in networks, but faces significant challenges from label scarcity and extreme class imbalance. While graph contrastive learning offers a promising unsupervised solution, existing…

Anomaly detection - identifying deviations from Standard Model predictions - is a key challenge at the Large Hadron Collider due to the size and complexity of its datasets. This is typically addressed by transforming high-dimensional…

Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables effective discrimination on anomalies. However, when…

Graph-based anomaly detection has been widely used for detecting malicious activities in real-world applications. Existing attempts to address this problem have thus far focused on structural feature engineering or learning in the binary…

Deep anomaly detection methods learn representations that separate between normal and anomalous images. Although self-supervised representation learning is commonly used, small dataset sizes limit its effectiveness. It was previously shown…

Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples. However, this might limit their adaptability to an increasing set of anomaly…

Medical image segmentation is a fundamental yet challenging task due to the arduous process of acquiring large volumes of high-quality labeled data from experts. Contrastive learning offers a promising but still problematic solution to this…

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly…

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…

In the anomaly detection field, the scarcity of anomalous samples has directed the current research emphasis towards unsupervised anomaly detection. While these unsupervised anomaly detection methods offer convenience, they also overlook…

Graph anomaly detection is a popular and vital task in various real-world scenarios, which has been studied for several decades. Recently, many studies extending deep learning-based methods have shown preferable performance on graph anomaly…

To date, the most common approach for radiology deep learning pipelines is the use of end-to-end 3D networks based on models pre-trained on other tasks, followed by fine-tuning on the task at hand. In contrast, adjacent medical fields such…

Contrastive learning is an effective unsupervised method in graph representation learning, and the key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the…

This paper is concerned with contrastive learning (CL) for low-level image restoration and enhancement tasks. We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an…