Related papers: Flow Mismatching: Unsupervised Anomaly Detection v…
Anomaly detection is defined as the problem of finding data points that do not follow the patterns of the majority. Among the various proposed methods for solving this problem, classification-based methods, including one-class Support…
Detecting anomalies in human-related videos is crucial for surveillance applications. Current methods primarily include appearance-based and action-based techniques. Appearance-based methods rely on low-level visual features such as color,…
Event-based motion field estimation is an important task. However, current optical flow methods face challenges: learning-based approaches, often frame-based and relying on CNNs, lack cross-domain transferability, while model-based methods,…
The multi-step denoising process in diffusion and Flow Matching models causes major efficiency issues, which motivates research on few-step generation. We present Solution Flow Models (SoFlow), a framework for one-step generation from…
Quantifying aleatoric uncertainty in medical image segmentation is critical since it is a reflection of the natural variability observed among expert annotators. A conventional approach is to model the segmentation distribution using the…
Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model…
In a variety of applications, one desires to detect groups of anomalous data samples, with a group potentially manifesting its atypicality (relative to a reference model) on a low-dimensional subset of the full measured set of features.…
Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity. However, they underperform in few-step sampling due to…
Anomaly detection is crucial for ensuring the stability and reliability of web service systems. Logs and metrics contain multiple information that can reflect the system's operational state and potential anomalies. Thus, existing anomaly…
Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods…
Recent efforts towards video anomaly detection (VAD) try to learn a deep autoencoder to describe normal event patterns with small reconstruction errors. The video inputs with large reconstruction errors are regarded as anomalies at the test…
While Flow Matching theoretically guarantees constant-velocity trajectories, we identify a critical breakdown in high-dimensional practice: the Velocity Deficit. We show that the MSE objective systematically underestimates velocity…
We present an improved clustering based, unsupervised anomalous trajectory detection algorithm for crowded scenes. The proposed work is based on four major steps, namely, extraction of trajectories from crowded scene video, extraction of…
Anomaly detection is important in many real-life applications. Recently, self-supervised learning has greatly helped deep anomaly detection by recognizing several geometric transformations. However these methods lack finer features, usually…
The external visual inspections of rolling stock's underfloor equipment are currently being performed via human visual inspection. In this study, we attempt to partly automate visual inspection by investigating anomaly inspection algorithms…
We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this distribution with a neural network. This lets us estimate…
Flow matching has shown state-of-the-art performance in various generative tasks, ranging from image generation to decision-making, where generation under energy guidance (abbreviated as guidance in the following) is pivotal. However, the…
Unsupervised pathology detection can be implemented by training a model on healthy data only and measuring the deviation from the training set upon inference, for example with CNN-based feature extraction and one-class classifiers, or…
Video anomaly detection (VAD) is an important computer vision problem. Thanks to the mode coverage capabilities of generative models, the likelihood-based paradigm is catching growing interest, as it can model normal distribution and detect…
This paper considers the generic problem of dense alignment between two images, whether they be two frames of a video, two widely different views of a scene, two paintings depicting similar content, etc. Whereas each such task is typically…