Improving Denoising Diffusion Probabilistic Models via Exploiting Shared
Representations
- URL: http://arxiv.org/abs/2311.16353v1
- Date: Mon, 27 Nov 2023 22:30:26 GMT
- Title: Improving Denoising Diffusion Probabilistic Models via Exploiting Shared
Representations
- Authors: Delaram Pirhayatifard, Mohammad Taha Toghani, Guha Balakrishnan,
C\'esar A. Uribe
- Abstract summary: SR-DDPM is a class of generative models that produce high-quality images by reversing a noisy diffusion process.
By exploiting the similarity between diverse data distributions, our method can scale to multiple tasks without compromising the image quality.
We evaluate our method on standard image datasets and show that it outperforms both unconditional and conditional DDPM in terms of FID and SSIM metrics.
- Score: 5.517338199249029
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: In this work, we address the challenge of multi-task image generation with
limited data for denoising diffusion probabilistic models (DDPM), a class of
generative models that produce high-quality images by reversing a noisy
diffusion process. We propose a novel method, SR-DDPM, that leverages
representation-based techniques from few-shot learning to effectively learn
from fewer samples across different tasks. Our method consists of a core meta
architecture with shared parameters, i.e., task-specific layers with exclusive
parameters. By exploiting the similarity between diverse data distributions,
our method can scale to multiple tasks without compromising the image quality.
We evaluate our method on standard image datasets and show that it outperforms
both unconditional and conditional DDPM in terms of FID and SSIM metrics.
Related papers
- SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder [13.453138169497903]
SeNM-VAE is a semi-supervised noise modeling method that leverages both paired and unpaired datasets to generate realistic degraded data.
We employ our method to generate paired training samples for real-world image denoising and super-resolution tasks.
Our approach excels in the quality of synthetic degraded images compared to other unpaired and paired noise modeling methods.
arXiv Detail & Related papers (2024-03-26T09:03:40Z) - Generalized Consistency Trajectory Models for Image Manipulation [59.576781858809355]
Diffusion-based generative models excel in unconditional generation, as well as on applied tasks such as image editing and restoration.
We propose generalized trajectory models (GCTMs) which translate between arbitrary distributions via ODEs.
We discuss the design space of GCTMs and demonstrate their efficacy in various image manipulation tasks such as image-to-image translation, restoration, and editing.
arXiv Detail & Related papers (2024-03-19T07:24:54Z) - Denoising Diffusion Bridge Models [54.87947768074036]
Diffusion models are powerful generative models that map noise to data using processes.
For many applications such as image editing, the model input comes from a distribution that is not random noise.
In our work, we propose Denoising Diffusion Bridge Models (DDBMs)
arXiv Detail & Related papers (2023-09-29T03:24:24Z) - Efficient Transfer Learning in Diffusion Models via Adversarial Noise [21.609168219488982]
Diffusion Probabilistic Models (DPMs) have demonstrated substantial promise in image generation tasks.
Previous works, like GANs, have tackled the limited data problem by transferring pre-trained models learned with sufficient data.
We propose a novel DPMs-based transfer learning method, TAN, to address the limited data problem.
arXiv Detail & Related papers (2023-08-23T06:44:44Z) - CDPMSR: Conditional Diffusion Probabilistic Models for Single Image
Super-Resolution [91.56337748920662]
Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation.
We propose a simple but non-trivial DPM-based super-resolution post-process framework,i.e., cDPMSR.
Our method surpasses prior attempts on both qualitative and quantitative results.
arXiv Detail & Related papers (2023-02-14T15:13:33Z) - SinDDM: A Single Image Denoising Diffusion Model [28.51951207066209]
We introduce a framework for training a Denoising diffusion model on a single image.
Our method, which we coin SinDDM, learns the internal statistics of the training image by using a multi-scale diffusion process.
It is applicable in a wide array of tasks, including style transfer and harmonization.
arXiv Detail & Related papers (2022-11-29T20:44:25Z) - Markup-to-Image Diffusion Models with Scheduled Sampling [111.30188533324954]
Building on recent advances in image generation, we present a data-driven approach to rendering markup into images.
The approach is based on diffusion models, which parameterize the distribution of data using a sequence of denoising operations.
We conduct experiments on four markup datasets: mathematical formulas (La), table layouts (HTML), sheet music (LilyPond), and molecular images (SMILES)
arXiv Detail & Related papers (2022-10-11T04:56:12Z) - Semantic Image Synthesis via Diffusion Models [159.4285444680301]
Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks.
Recent work on semantic image synthesis mainly follows the emphde facto Generative Adversarial Nets (GANs)
arXiv Detail & Related papers (2022-06-30T18:31:51Z) - ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models [22.84873720309945]
We propose Iterative Latent Variable Refinement (ILVR) to guide the generative process in DDPM to generate high-quality images.
The proposed ILVR method generates high-quality images while controlling the generation.
arXiv Detail & Related papers (2021-08-06T04:43:13Z) - A Hierarchical Transformation-Discriminating Generative Model for Few
Shot Anomaly Detection [93.38607559281601]
We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image.
The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions.
arXiv Detail & Related papers (2021-04-29T17:49:48Z)
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.