Efficient Multimodal Diffusion Models Using Joint Data Infilling with Partially Shared U-Net
Hu, Zizhao, Jia, Shaochong, Rostami, Mohammad
–arXiv.org Artificial Intelligence
Recently, diffusion models have been used successfully to fit distributions for cross-modal data translation and multimodal data generation. However, these methods rely on extensive scaling, overlooking the inefficiency and interference between modalities. We develop Partially Shared U-Net (PS-U-Net) architecture which is an efficient multimodal diffusion model that allows text and image inputs to pass through dedicated layers and skip-connections for preserving modality-specific fine-grained details. Inspired by image inpainting, we also propose a new efficient multimodal sampling method that introduces new scenarios for conditional generation while only requiring a simple joint distribution to be learned. Our empirical exploration of the MS-COCO dataset demonstrates that our method generates multimodal text and image data with higher quality compared to existing multimodal diffusion models while having a comparable size, faster training, faster multimodal sampling, and more flexible generation.
arXiv.org Artificial Intelligence
Nov-27-2023
- Country:
- North America > United States > California > Los Angeles County > Los Angeles (0.28)
- Genre:
- Research Report (0.50)
- Industry:
- Leisure & Entertainment > Sports (0.68)
- Education (0.46)
- Health & Medicine > Therapeutic Area
- Neurology (0.46)
- Technology: