تقرير
DiffiT: Diffusion Vision Transformers for Image Generation
| العنوان: | DiffiT: Diffusion Vision Transformers for Image Generation |
|---|---|
| المؤلفون: | Hatamizadeh, Ali, Song, Jiaming, Liu, Guilin, Kautz, Jan, Vahdat, Arash |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning |
| الوصف: | Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities and scalability, especially for recognition tasks. In this paper, we study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT). Specifically, we propose a methodology for finegrained control of the denoising process and introduce the Time-dependant Multihead Self Attention (TMSA) mechanism. DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency. We also propose latent and image space DiffiT models and show SOTA performance on a variety of class-conditional and unconditional synthesis tasks at different resolutions. The Latent DiffiT model achieves a new SOTA FID score of 1.73 on ImageNet-256 dataset while having 19.85%, 16.88% less parameters than other Transformer-based diffusion models such as MDT and DiT, respectively. Code: https://github.com/NVlabs/DiffiT Comment: Revised Tech report |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2312.02139 |
| رقم الأكسشن: | edsarx.2312.02139 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |