Research
Continuous Adversarial MeanFlow Transfer
arXiv:2608.19540v1 Announce Type: cross Abstract: Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to
arXiv:2608.19540v1 Announce Type: cross Abstract: Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to a new domain leaves its costly multi-step sampling unaddressed, and existing acceleration methods are tied to the source parameterization--epsilon, x, v, or u--leaving heterogeneous pretrained models with no common acceleration target. Second, while adversarial refinement is proven effective for few-step quality, it is formulated only for instantaneous-velocity flows, not for the finite-interval average velocities that MeanFlow (MF) models predict. We address both problems. We propose MeanFlow-Transfer, which maps heterogeneous source outputs into a shared velocity representation, uses it to initialize an MF generator from the source weights, and optimizes an MF objective on the target domain. This unifies adaptation and acceleration in a single training loop across a broad range of pretrained models. We then introduce Continuous Adversarial MeanFlow, a post-training stage that extends continuous adversarial flow models from instantaneous velocities to MF's finite-interval average velocities. CAMF contrasts changes in a learned potential between real and predicted interval endpoints, recovering fine detail that MF regression averages away, and reduces to the instantaneous criterion in the vanishing-interval limit. Adapting four ImageNet-based source models--DiT (epsilon), SiT (v), JiT (x), iMF (u)--to five target domains, MF-T with CAMF matches or exceeds the fine-tuned teacher in FID and FDD at up to 125imes fewer Neural Function Evaluations (NFEs), while CAMF improves MF-T's few-step FID by 29% on average.
Related
- Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection
- A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models
- Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis
- Exploring and Exploiting Stability in Latent Flow Matching
Source: arXiv cs.CV | 2026-08-21