Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2504.13499 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911167198265344 |
|---|---|
| author | Ergasti, Alex Botti, Filippo Fontanini, Tomaso Ferrari, Claudio Bertozzi, Massimo Prati, Andrea |
| author_facet | Ergasti, Alex Botti, Filippo Fontanini, Tomaso Ferrari, Claudio Bertozzi, Massimo Prati, Andrea |
| contents | Diffusion models have become the most popular approach for high-quality image generation, but their high computational cost still remains a significant challenge. To address this problem, we propose U-Shape Mamba (USM), a novel diffusion model that leverages Mamba-based layers within a U-Net-like hierarchical structure. By progressively reducing sequence length in the encoder and restoring it in the decoder through Mamba blocks, USM significantly lowers computational overhead while maintaining strong generative capabilities. Experimental results against Zigma, which is currently the most efficient Mamba-based diffusion model, demonstrate that USM achieves one-third the GFlops, requires less memory and is faster, while outperforming Zigma in image quality. Frechet Inception Distance (FID) is improved by 15.3, 0.84 and 2.7 points on AFHQ, CelebAHQ and COCO datasets, respectively. These findings highlight USM as a highly efficient and scalable solution for diffusion-based generative models, making high-quality image synthesis more accessible to the research community while reducing computational costs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13499 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | U-Shape Mamba: State Space Model for faster diffusion Ergasti, Alex Botti, Filippo Fontanini, Tomaso Ferrari, Claudio Bertozzi, Massimo Prati, Andrea Computer Vision and Pattern Recognition Diffusion models have become the most popular approach for high-quality image generation, but their high computational cost still remains a significant challenge. To address this problem, we propose U-Shape Mamba (USM), a novel diffusion model that leverages Mamba-based layers within a U-Net-like hierarchical structure. By progressively reducing sequence length in the encoder and restoring it in the decoder through Mamba blocks, USM significantly lowers computational overhead while maintaining strong generative capabilities. Experimental results against Zigma, which is currently the most efficient Mamba-based diffusion model, demonstrate that USM achieves one-third the GFlops, requires less memory and is faster, while outperforming Zigma in image quality. Frechet Inception Distance (FID) is improved by 15.3, 0.84 and 2.7 points on AFHQ, CelebAHQ and COCO datasets, respectively. These findings highlight USM as a highly efficient and scalable solution for diffusion-based generative models, making high-quality image synthesis more accessible to the research community while reducing computational costs. |
| title | U-Shape Mamba: State Space Model for faster diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.13499 |