Related papers: Self-Supervised Masking for Unsupervised Anomaly D…

Deep anomaly detection models using a supervised mode of learning usually work under a closed set assumption and suffer from overfitting to previously seen rare anomalies at training, which hinders their applicability in a real scenario. In…

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…

This paper proposes a method to ease the unsupervised learning of object landmark detectors. Similarly to previous methods, our approach is fully unsupervised in a sense that it does not require or make any use of annotated landmarks for…

The increasing complexity of medical imaging data underscores the need for advanced anomaly detection methods to automatically identify diverse pathologies. Current methods face challenges in capturing the broad spectrum of anomalies, often…

Current deep learning methods for anomaly detection in text rely on supervisory signals in inliers that may be unobtainable or bespoke architectures that are difficult to tune. We study a simpler alternative: fine-tuning Transformers on the…

We propose the Autoencoding Binary Classifiers (ABC), a novel supervised anomaly detector based on the Autoencoder (AE). There are two main approaches in anomaly detection: supervised and unsupervised. The supervised approach accurately…

Masked reconstruction serves as a fundamental pretext task for self-supervised learning, enabling the model to enhance its feature extraction capabilities by reconstructing the masked segments from extensive unlabeled data. In human…

Anomaly detection is the task of identifying abnormal behavior of a system. Anomaly detection in computational workflows is of special interest because of its wide implications in various domains such as cybersecurity, finance, and social…

Self-supervised learning has shown great promise due to its capability to train deep learning MRI reconstruction methods without fully-sampled data. Current self-supervised learning methods for physics-guided reconstruction networks split…

Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. However,…

Neural network-based anomaly detection methods have shown to achieve high performance. However, they require a large amount of training data for each task. We propose a neural network-based meta-learning method for supervised anomaly…

Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains an open problem due to the data sparsity and scene…

An image anomaly localization method based on the successive subspace learning (SSL) framework, called AnomalyHop, is proposed in this work. AnomalyHop consists of three modules: 1) feature extraction via successive subspace learning (SSL),…

Unsupervised anomaly detection is vital in industrial fields, with reconstruction-based methods favored for their simplicity and effectiveness. However, reconstruction methods often encounter an identical shortcut issue, where both normal…

In this work, we explore Self-supervised Learning (SSL) as an auxiliary task to blend the texture-based local descriptors into feature modelling for efficient face analysis. Combining a primary task and a self-supervised auxiliary task is…

Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the cost of requiring a large set of high…

Driver distraction causes a significant number of traffic accidents every year, resulting in economic losses and casualties. Currently, the level of automation in commercial vehicles is far from completely unmanned, and drivers still play…

This paper presents a novel approach to learn and detect distinctive regions on 3D shapes. Unlike previous works, which require labeled data, our method is unsupervised. We conduct the analysis on point sets sampled from 3D shapes, then…

Self-supervised learning (SSL) methods have become a dominant paradigm for creating general purpose models whose capabilities can be transferred to downstream supervised learning tasks. However, most such methods rely on vast amounts of…

In current biological and medical research, statistical shape modeling (SSM) provides an essential framework for the characterization of anatomy/morphology. Such analysis is often driven by the identification of a relatively small number of…