AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
arxiv(2023)
摘要
Existing customization methods require access to multiple reference examples
to align pre-trained diffusion probabilistic models (DPMs) with user-provided
concepts. This paper aims to address the challenge of DPM customization when
the only available supervision is a differentiable metric defined on the
generated contents. Since the sampling procedure of DPMs involves recursive
calls to the denoising UNet, naïve gradient backpropagation requires storing
the intermediate states of all iterations, resulting in extremely high memory
consumption. To overcome this issue, we propose a novel method AdjointDPM,
which first generates new samples from diffusion models by solving the
corresponding probability-flow ODEs. It then uses the adjoint sensitivity
method to backpropagate the gradients of the loss to the models' parameters
(including conditioning signals, network weights, and initial noises) by
solving another augmented ODE. To reduce numerical errors in both the forward
generation and gradient backpropagation processes, we further reparameterize
the probability-flow ODE and augmented ODE as simple non-stiff ODEs using
exponential integration. Finally, we demonstrate the effectiveness of
AdjointDPM on three interesting tasks: converting visual effects into
identification text embeddings, finetuning DPMs for specific types of
stylization, and optimizing initial noise to generate adversarial samples for
security auditing.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要