Related papers: FlowCLAS: Enhancing Normalizing Flow Via Contrasti…

The purpose of training neural networks is to achieve high generalization performance on unseen inputs. However, when trained on imbalanced datasets, a model's prediction tends to favor majority classes over minority classes, leading to…

Unsupervised anomaly detection and localization is crucial to the practical application when collecting and labeling sufficient anomaly data is infeasible. Most existing representation-based approaches extract normal image features with a…

Unsupervised anomaly detection is coming into the spotlight these days in various practical domains due to the limited amount of anomaly data. One of the major approaches for it is a normalizing flow which pursues the invertible…

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…

Despite significant advances in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has…

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…

This paper addresses the increasingly prominent problem of anomaly detection in distributed systems. It proposes a detection method based on federated contrastive learning. The goal is to overcome the limitations of traditional centralized…

For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single…

Normalizing Flows (NFs) are able to model complicated distributions p(y) with strong inter-dimensional correlations and high multimodality by transforming a simple base density p(z) through an invertible neural network under the change of…

We propose FlowSVDD -- a flow-based one-class classifier for anomaly/outliers detection that realizes a well-known SVDD principle using deep learning tools. Contrary to other approaches to deep SVDD, the proposed model is instantiated using…

We introduce Time-Conditioned Contraction Matching (TCCM), a novel method for semi-supervised anomaly detection in tabular data. TCCM is inspired by flow matching, a recent generative modeling framework that learns velocity fields between…

Learning to detect real-world anomalous events through video-level labels is a challenging task due to the rare occurrence of anomalies as well as noise in the labels. In this work, we propose a weakly supervised anomaly detection method…

Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and…

The sophistication and diversity of contemporary cyberattacks have rendered the use of proxies, gateways, firewalls, and encrypted tunnels as a standalone defensive strategy inadequate. Consequently, the proactive identification of data…

Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the simpler setting of homogeneous, dense prediction tasks,…

Continuous Normalizing Flows (CNFs) have emerged as promising deep generative models for a wide range of tasks thanks to their invertibility and exact likelihood estimation. However, conditioning CNFs on signals of interest for conditional…

Recent advances in Vision-Language-Action (VLA) models have enabled robots to execute increasingly complex tasks. However, VLA models trained through imitation learning struggle to operate reliably in dynamic environments and often fail…

Given datasets from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many contexts, such as cross-domain translation and domain…

Machine Learning (ML) models in Robotic Assembly Sequence Planning (RASP) need to be introspective on the predicted solutions, i.e. whether they are feasible or not, to circumvent potential efficiency degradation. Previous works need both…

Continual learning in robotics seeks systems that can constantly adapt to changing environments and tasks, mirroring human adaptability. A key challenge is refining dynamics models, essential for planning and control, while addressing…