Improved Diffusion-based Generative Model with Better Adversarial Robustness

• URL: http://arxiv.org/abs/2502.17099v1
• Date: Mon, 24 Feb 2025 12:29:16 GMT
• Title: Improved Diffusion-based Generative Model with Better Adversarial Robustness
• Authors: Zekun Wang, Mingyang Yi, Shuchen Xue, Zhenguo Li, Ming Liu, Bing Qin, Zhi-Ming Ma,
• Abstract summary: Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks.<n>During the denoising process, the input data distributions differ between the training and inference stages.
• Score: 65.38540020916432
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks. However, their training and sampling processes suffer from the issue of distribution mismatch. During the denoising process, the input data distributions differ between the training and inference stages, potentially leading to inaccurate data generation. To obviate this, we analyze the training objective of DPMs and theoretically demonstrate that this mismatch can be alleviated through Distributionally Robust Optimization (DRO), which is equivalent to performing robustness-driven Adversarial Training (AT) on DPMs. Furthermore, for the recently proposed Consistency Model (CM), which distills the inference process of the DPM, we prove that its training objective also encounters the mismatch issue. Fortunately, this issue can be mitigated by AT as well. Based on these insights, we propose to conduct efficient AT on both DPM and CM. Finally, extensive empirical studies validate the effectiveness of AT in diffusion-based models. The code is available at https://github.com/kugwzk/AT_Diff.

Related papers

• Extracting Training Data from Unconditional Diffusion Models [32.18993348942877]
  Diffusion probabilistic models (DPMs) are being employed as mainstream models for Generative Artificial Intelligence (GenAI)<n>We propose a novel data extraction method named textbfSurrogate condItional Data Extraction (SIDE) that leverages a time-dependent trained on generated data as surrogate conditions to extract training data from unconditional DPMs.
  arXiv  Detail & Related papers  (2024-10-03T13:17:06Z)
• Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models [33.09663675904689]
  We investigate efficient diffusion training from the perspective of dataset pruning. Inspired by the principles of data-efficient training for generative models such as generative adversarial networks (GANs), we first extend the data selection scheme used in GANs to DM training. To further improve the generation performance, we employ a class-wise reweighting approach.
  arXiv  Detail & Related papers  (2024-09-27T20:21:19Z)
• Unsupervised Domain Adaptation Via Data Pruning [0.0]
  We consider the problem from the perspective of unsupervised domain adaptation (UDA) We propose AdaPrune, a method for UDA whereby training examples are removed to attempt to align the training distribution to that of the target data. As a method for UDA, we show that AdaPrune outperforms related techniques, and is complementary to other UDA algorithms such as CORAL.
  arXiv  Detail & Related papers  (2024-09-18T15:48:59Z)
• Contractive Diffusion Probabilistic Models [5.217870815854702]
  Diffusion probabilistic models (DPMs) have emerged as a promising technique in generative modeling. We propose a new criterion -- the contraction property of backward sampling in the design of DPMs, leading to a novel class of contractive DPMs (CDPMs) We show that CDPM can leverage weights of pretrained DPMs by a simple transformation, and does not need retraining.
  arXiv  Detail & Related papers  (2024-01-23T21:51:51Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training. It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models. While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
  Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps. We introduce a novel approach that tackles the problem by matching implicit and explicit factors. We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
  arXiv  Detail & Related papers  (2023-06-21T18:49:22Z)
• Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models [37.18522296366212]
  Diffusion probabilistic models (DPMs) are a class of powerful deep generative models (DGMs) Despite their success, the iterative generation process over the full timesteps is much less efficient than other DGMs such as GANs. We consider diagonal and full covariances to improve the expressive power of DPMs.
  arXiv  Detail & Related papers  (2022-06-15T05:42:48Z)
• Accelerating Diffusion Models via Early Stop of the Diffusion Process [114.48426684994179]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved impressive performance on various generation tasks. In practice DDPMs often need hundreds even thousands of denoising steps to obtain a high-quality sample. We propose a principled acceleration strategy, referred to as Early-Stopped DDPM (ES-DDPM), for DDPMs.
  arXiv  Detail & Related papers  (2022-05-25T06:40:09Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Denoising Diffusion Implicit Models [117.03720513930335]
  We present denoising diffusion implicit models (DDIMs) for iterative implicit probabilistic models with the same training procedure as DDPMs. DDIMs can produce high quality samples $10 times$ to $50 times$ faster in terms of wall-clock time compared to DDPMs.
  arXiv  Detail & Related papers  (2020-10-06T06:15:51Z)

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.