| license: mit | |
| pipeline_tag: unconditional-image-generation | |
| tags: | |
| - flow-matching | |
| - image-generation | |
| # VeCoR: Velocity Contrastive Regularization for Flow Matching | |
| [**Paper**](https://arxiv.org/abs/2511.18942) | [**Project Page**](https://p458732.github.io/VeCoR_Project_Page/) | [**GitHub**](https://github.com/p458732/VeCoR) | |
| Velocity Contrastive Regularization (**VeCoR**) is a complementary training scheme for flow-based generative modeling that augments the standard Flow Matching (FM) objective with contrastive, two-sided supervision. VeCoR not only aligns the predicted velocity with a stable reference direction (positive supervision) but also pushes it away from inconsistent, off-manifold directions (negative supervision). | |
| This formulation transforms FM from a purely attractive, one-sided objective into a two-sided training signal, regularizing trajectory evolution and improving perceptual fidelity across datasets and backbones, particularly in low-step and lightweight settings. | |
| ## Performance | |
| On ImageNet-1K 256x256, VeCoR achieves **FID=1.94** (SiT-XL/2 backbone), demonstrating significant gains in stability and image quality. It also shows consistent improvements in MS-COCO text-to-image generation. | |
| ## Usage | |
| Please refer to the [official GitHub repository](https://github.com/p458732/VeCoR) for environment setup, training, and sampling instructions using the provided scripts. | |
| ## Citation | |
| ```bibtex | |
| @misc{hong2025vecorvelocitycontrastive, | |
| title={VeCoR - Velocity Contrastive Regularization for Flow Matching}, | |
| author={Zong-Wei Hong and Jing-lun Li and Lin-Ze Li and Shen Zhang and Yao Tang}, | |
| year={2025}, | |
| eprint={2511.18942}, | |
| archivePrefix={arXiv}, | |
| primaryClass={cs.CV}, | |
| url={https://arxiv.org/abs/2511.18942}, | |
| } | |
| ``` |