Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models

• URL: http://arxiv.org/abs/2605.23070v1
• Date: Thu, 21 May 2026 22:01:31 GMT
• Title: Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
• Abstract summary: unsupervised anomaly detection method that deliberately avoids reconstruction-based paradigms.<n>We treat flow matching as geometric dynamics and leverage a key insight: anomalies occur at places where the learned normal flow disagrees with the geometric path toward a test image.
• Score: 4.861045498353029
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 the learned normal flow disagrees with the geometric path toward a test image. Given a flow matching model trained only on normal images, we probe its learned velocity field along affine paths from Gaussian noise to a target image. Along each path, we compare the model-predicted velocity, which follows normal generative dynamics, with the geometric velocity toward the target, which includes any anomalous content. Anomalies induce strong local disagreement between these velocities. Aggregating the mismatch over different time steps and multiple paths yields pixel-wise heatmaps and image-level scores without test-time optimization, feature memories, or additional calibration. Our analysis shows that the population mismatch decomposes into an irreducible denoising term and a Fisher-divergence term between the test-path and normal-path score functions, which identifies the score-gap component that drives anomaly separation and explains the effectiveness of robust path aggregation. Extensive experiments on MVTec-AD and VisA demonstrate superior performance compared with SOTA reconstruction-based and recent flow matching-based approaches.

Related papers

• Probability-Conserving Flow Guidance [49.03107678763765]
  Adaptive Manifold Guidance (AdaMaG) improves realism, reduces hallucinations, and controlled desaturation in high-guidance.<n>Across image generation benchmarks, AdaMaG improves realism, reduces hallucinations, and controlled desaturation in high-guidance.
  arXiv  Detail & Related papers  (2026-05-19T16:34:01Z)
• Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency [74.90075313101933]
  This paper revisits the same optical-flow primitive through a more local supervision design.<n>We use adjacent-frame Eulerian motion fields to guide generation, where the motion signal always describes a short temporal hop.<n>To mitigate the drift artifacts common in adjacent frame generation, we introduce a Bidirectional Geometric Consistency mechanism.
  arXiv  Detail & Related papers  (2026-05-07T13:53:31Z)
• FlowConsist: Make Your Flow Consistent with Real Trajectory [99.22869983378062]
  We argue that current fast-flow training paradigms suffer from two fundamental issues.<n> conditional velocities constructed from randomly paired noise-data samples introduce systematic trajectory drift.<n>We propose FlowConsist, a training framework designed to enforce trajectory consistency in fast flows.
  arXiv  Detail & Related papers  (2026-02-06T03:24:23Z)
• Temporal Pair Consistency for Variance-Reduced Flow Matching [13.328987133593154]
  Temporal Pair Consistency (TPC) is a lightweight variance-reduction principle that couples velocity predictions at paired timesteps along the same probability path.<n>Instantiated within flow matching, TPC improves sample quality and efficiency across CIFAR-10 and ImageNet at multiple resolutions.
  arXiv  Detail & Related papers  (2026-02-04T00:05:21Z)
• FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification [14.643457217551484]
  We propose FlowPath, a novel approach that learns the geometry of the control path via an invertible neural flow.<n>We show that FlowPath consistently achieves statistically significant improvements in classification accuracy over baselines using fixed interpolants or non-invertible architectures.
  arXiv  Detail & Related papers  (2025-11-13T22:59:26Z)
• OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching [14.664226708184676]
  Flow-based text-to-image models follow deterministic trajectories, forcing users to repeatedly sample to discover diverse modes.<n>We present a training-free, inference-time control mechanism that makes the flow itself diversity-aware.
  arXiv  Detail & Related papers  (2025-10-10T07:07:19Z)
• Purrception: Variational Flow Matching for Vector-Quantized Image Generation [79.74708247230218]
  Purrception is a variational flow matching approach for vector-quantized image generation.<n>Our method adapts Variational Flow Matching to vector-quantized latents by learning categorical posteriors over codebook indices.<n>This combines the geometric awareness of continuous methods with the discrete supervision of categorical approaches.
  arXiv  Detail & Related papers  (2025-10-01T21:41:30Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• On the Robustness of Normalizing Flows for Inverse Problems in Imaging [16.18759484251522]
  Unintended severe artifacts are occasionally observed in the output of Conditional normalizing flows. We empirically and theoretically reveal that these problems are caused by exploding variance'' in the conditional affine coupling layer. We suggest a simple remedy that substitutes the affine coupling layers with the modified rational quadratic spline coupling layers in normalizing flows.
  arXiv  Detail & Related papers  (2022-12-08T15:18:28Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Conditional Injective Flows for Bayesian Imaging [18.561430512510956]
  Injectivity reduces memory footprint and training time while low-dimensional latent space together with architectural innovations. C-Trumpets enable fast approximation of point estimates like MMSE or MAP as well as physically-meaningful uncertainty quantification.
  arXiv  Detail & Related papers  (2022-04-15T22:26:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.