Related papers: On Uniformly Scaling Flows: A Density-Aligned Appr…

Unsupervised anomaly detection with localization has many practical applications when labeling is infeasible and, moreover, when anomaly examples are completely missing in the train data. While recently proposed models for such data setup…

Federated Learning (FL) often suffers from severe performance degradation when faced with non-IID data, largely due to local classifier bias. Traditional remedies such as global model regularization or layer freezing either incur high…

Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: 1) If the target distribution is manifold, due to the unmatch between the dimensions of the latent target distribution…

Deep-learning methods have shown promising performance for low-dose computed tomography (LDCT) reconstruction. However, supervised methods face the problem of lacking labeled data in clinical scenarios, and the CNN-based unsupervised…

Classical approaches for one-class problems such as one-class SVM and isolation forest require careful feature engineering when applied to structured domains like images. State-of-the-art methods aim to leverage deep learning to learn…

Anomaly activities such as robbery, explosion, accidents, etc. need immediate actions for preventing loss of human life and property in real world surveillance systems. Although the recent automation in surveillance systems are capable of…

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…

Many systems in physics, engineering, and biology exhibit multiscale stochastic dynamics, where low-dimensional slow variables evolve under the influence of high-dimensional fast processes. In practice, observations are often limited to a…

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term…

We consider the problem of density estimation on Riemannian manifolds. Density estimation on manifolds has many applications in fluid-mechanics, optics and plasma physics and it appears often when dealing with angular variables (such as…

Anomaly detection in videos is challenging due to the complexity, noise, and diverse nature of activities such as violence, shoplifting, and vandalism. While deep learning (DL) has shown excellent performance in this area, existing…

Vessel segmentation is an essential task in many clinical applications. Although supervised methods have achieved state-of-art performance, acquiring expert annotation is laborious and mostly limited for two-dimensional datasets with a…

We present the first implementation of a Continuous Normalizing Flow (CNF) model for unsupervised anomaly detection within the realistic, high-rate environment of the Large Hadron Collider's L1 trigger systems. While CNFs typically define…

Many application domains, spanning from computational photography to medical imaging, require recovery of high-fidelity images from noisy, incomplete or partial/compressed measurements. State of the art methods for solving these inverse…

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…

Tabular regression is a well-studied problem with numerous industrial applications, yet most existing approaches focus on point estimation, often leading to overconfident predictions. This issue is particularly critical in industrial…

We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows to learn…

We are interested in learning generative models for complex geometries described via manifolds, such as spheres, tori, and other implicit surfaces. Current extensions of existing (Euclidean) generative models are restricted to specific…

Underwater Salient Object Detection (USOD) faces significant challenges, including underwater image quality degradation and domain gaps. Existing methods tend to ignore the physical principles of underwater imaging or simply treat…

Normalizing Flows (NFs) are emerging as a powerful class of generative models, as they not only allow for efficient sampling, but also deliver, by construction, density estimation. They are of great potential usage in High Energy Physics…