Efficient Denoising using Score Embedding in Score-based Diffusion Models
This work addresses a computational bottleneck for researchers and practitioners using diffusion models, though it is incremental as it builds on existing score-based methods.
The paper tackles the inefficiency of training denoising score-based diffusion models, which typically require many epochs and large datasets, by proposing a method that pre-computes scores using the log-density Fokker-Planck Equation to embed them into images, resulting in faster training with fewer epochs and images while maintaining similar quality.
It is well known that training a denoising score-based diffusion models requires tens of thousands of epochs and a substantial number of image data to train the model. In this paper, we propose to increase the efficiency in training score-based diffusion models. Our method allows us to decrease the number of epochs needed to train the diffusion model. We accomplish this by solving the log-density Fokker-Planck (FP) Equation numerically to compute the score \textit{before} training. The pre-computed score is embedded into the image to encourage faster training under slice Wasserstein distance. Consequently, it also allows us to decrease the number of images we need to train the neural network to learn an accurate score. We demonstrate through our numerical experiments the improved performance of our proposed method compared to standard score-based diffusion models. Our proposed method achieves a similar quality to the standard method meaningfully faster.