Saved in:
Bibliographic Details
Main Authors: Lee, Hansang, Lee, Chaelin, Seo, Nieun, Lim, Joon Seok, Hong, Helen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.22406
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912791070244864
author Lee, Hansang
Lee, Chaelin
Seo, Nieun
Lim, Joon Seok
Hong, Helen
author_facet Lee, Hansang
Lee, Chaelin
Seo, Nieun
Lim, Joon Seok
Hong, Helen
contents We propose DeFloMat (Detection with Flow Matching), a novel generative object detection framework that addresses the critical latency bottleneck of diffusion-based detectors, such as DiffusionDet, by integrating Conditional Flow Matching (CFM). Diffusion models achieve high accuracy by formulating detection as a multi-step stochastic denoising process, but their reliance on numerous sampling steps ($T \gg 60$) makes them impractical for time-sensitive clinical applications like Crohn's Disease detection in Magnetic Resonance Enterography (MRE). DeFloMat replaces this slow stochastic path with a highly direct, deterministic flow field derived from Conditional Optimal Transport (OT) theory, specifically approximating the Rectified Flow. This shift enables fast inference via a simple Ordinary Differential Equation (ODE) solver. We demonstrate the superiority of DeFloMat on a challenging MRE clinical dataset. Crucially, DeFloMat achieves state-of-the-art accuracy ($43.32\% \text{ } AP_{10:50}$) in only $3$ inference steps, which represents a $1.4\times$ performance improvement over DiffusionDet's maximum converged performance ($31.03\% \text{ } AP_{10:50}$ at $4$ steps). Furthermore, our deterministic flow significantly enhances localization characteristics, yielding superior Recall and stability in the few-step regime. DeFloMat resolves the trade-off between generative accuracy and clinical efficiency, setting a new standard for stable and rapid object localization.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22406
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeFloMat: Detection with Flow Matching for Stable and Efficient Generative Object Localization
Lee, Hansang
Lee, Chaelin
Seo, Nieun
Lim, Joon Seok
Hong, Helen
Computer Vision and Pattern Recognition
We propose DeFloMat (Detection with Flow Matching), a novel generative object detection framework that addresses the critical latency bottleneck of diffusion-based detectors, such as DiffusionDet, by integrating Conditional Flow Matching (CFM). Diffusion models achieve high accuracy by formulating detection as a multi-step stochastic denoising process, but their reliance on numerous sampling steps ($T \gg 60$) makes them impractical for time-sensitive clinical applications like Crohn's Disease detection in Magnetic Resonance Enterography (MRE). DeFloMat replaces this slow stochastic path with a highly direct, deterministic flow field derived from Conditional Optimal Transport (OT) theory, specifically approximating the Rectified Flow. This shift enables fast inference via a simple Ordinary Differential Equation (ODE) solver. We demonstrate the superiority of DeFloMat on a challenging MRE clinical dataset. Crucially, DeFloMat achieves state-of-the-art accuracy ($43.32\% \text{ } AP_{10:50}$) in only $3$ inference steps, which represents a $1.4\times$ performance improvement over DiffusionDet's maximum converged performance ($31.03\% \text{ } AP_{10:50}$ at $4$ steps). Furthermore, our deterministic flow significantly enhances localization characteristics, yielding superior Recall and stability in the few-step regime. DeFloMat resolves the trade-off between generative accuracy and clinical efficiency, setting a new standard for stable and rapid object localization.
title DeFloMat: Detection with Flow Matching for Stable and Efficient Generative Object Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.22406