Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models

• URL: http://arxiv.org/abs/2312.12487v1
• Date: Tue, 19 Dec 2023 17:08:48 GMT
• Title: Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
• Authors: Angela Castillo, Jonas Kohler, Juan C. P\'erez, Juan Pablo P\'erez, Albert Pumarola, Bernard Ghanem, Pablo Arbel\'aez, Ali Thabet
• Abstract summary: "Adaptive Guidance" (AG) is an efficient variant of computation-Free Guidance (CFG) AG preserves CFG's image quality while reducing by 25%. " LinearAG" offers even cheaper inference at the cost of deviating from the baseline model.
• Score: 44.58960475893552
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This paper presents a comprehensive study on the role of Classifier-Free Guidance (CFG) in text-conditioned diffusion models from the perspective of inference efficiency. In particular, we relax the default choice of applying CFG in all diffusion steps and instead search for efficient guidance policies. We formulate the discovery of such policies in the differentiable Neural Architecture Search framework. Our findings suggest that the denoising steps proposed by CFG become increasingly aligned with simple conditional steps, which renders the extra neural network evaluation of CFG redundant, especially in the second half of the denoising process. Building upon this insight, we propose "Adaptive Guidance" (AG), an efficient variant of CFG, that adaptively omits network evaluations when the denoising process displays convergence. Our experiments demonstrate that AG preserves CFG's image quality while reducing computation by 25%. Thus, AG constitutes a plug-and-play alternative to Guidance Distillation, achieving 50% of the speed-ups of the latter while being training-free and retaining the capacity to handle negative prompts. Finally, we uncover further redundancies of CFG in the first half of the diffusion process, showing that entire neural function evaluations can be replaced by simple affine transformations of past score estimates. This method, termed LinearAG, offers even cheaper inference at the cost of deviating from the baseline model. Our findings provide insights into the efficiency of the conditional denoising process that contribute to more practical and swift deployment of text-conditioned diffusion models.

Related papers

• Rectified Diffusion Guidance for Conditional Generation [62.00207951161297]
  We revisit the theory behind CFG and rigorously confirm that the improper configuration of the combination coefficients (i.e., the widely used summing-to-one version) brings about expectation shift of the generative distribution. We propose ReCFG with a relaxation on the guidance coefficients such that denoising with ReCFG strictly aligns with the diffusion theory. That way the rectified coefficients can be readily pre-computed via traversing the observed data, leaving the sampling speed barely affected.
  arXiv  Detail & Related papers  (2024-10-24T13:41:32Z)
• Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models [27.640009920058187]
  We revisit the CFG update rule and introduce modifications to address this issue. We propose down-weighting the parallel component to achieve high-quality generations without oversaturation. We also introduce a new rescaling momentum method for the CFG update rule based on this insight.
  arXiv  Detail & Related papers  (2024-10-03T12:06:29Z)
• Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders [101.42201747763178]
  Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Our work provides a novel disentanglement mechanism to build an efficient pre-training purification method.
  arXiv  Detail & Related papers  (2024-05-02T16:49:25Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Observation-Guided Diffusion Probabilistic Models [41.749374023639156]
  We propose a novel diffusion-based image generation method called the observation-guided diffusion probabilistic model (OGDM) Our approach reestablishes the training objective by integrating the guidance of the observation process with the Markov chain. We demonstrate the effectiveness of our training algorithm using diverse inference techniques on strong diffusion model baselines.
  arXiv  Detail & Related papers  (2023-10-06T06:29:06Z)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)
• Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints [15.296955630621566]
  Constr-DRKM is a deep kernel method for the unsupervised learning of disentangled data representations. We quantitatively evaluate the proposed method's effectiveness in disentangled feature learning.
  arXiv  Detail & Related papers  (2020-11-25T11:40:10Z)
• Detached Error Feedback for Distributed SGD with Random Sparsification [98.98236187442258]
  Communication bottleneck has been a critical problem in large-scale deep learning. We propose a new distributed error feedback (DEF) algorithm, which shows better convergence than error feedback for non-efficient distributed problems. We also propose DEFA to accelerate the generalization of DEF, which shows better bounds than DEF.
  arXiv  Detail & Related papers  (2020-04-11T03:50:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.