Related papers: Your Image Generator Is Your New Private Dataset

We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation used to condition diffusion models from the perspective that…

Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…

Recent deep generative models (DGMs) such as generative adversarial networks (GANs) and diffusion probabilistic models (DPMs) have shown their impressive ability in generating high-fidelity photorealistic images. Although looking appealing…

Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation, which transfers knowledge from a complex teacher to a…

High-quality power flow datasets are essential for training machine learning models in power systems. However, security and privacy concerns restrict access to real-world data, making statistically accurate and physically consistent…

In this paper, we present an automated pipeline for generating domain-specific synthetic datasets with diffusion models, addressing the distribution shift between pre-trained models and real-world deployment environments. Our three-stage…

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

Conditional image generation models have achieved remarkable results by leveraging text-based control to generate customized images. However, the high resource demands of these models and the scarcity of well-annotated data have hindered…

Tabular data synthesis aims to generate high-quality data while preserving privacy. However, we find that existing tabular generative models exhibit a clear tradeoff in the small-data regime: improving data quality typically comes at the…

Despite continued advancement in recent years, deep neural networks still rely on large amounts of training data to avoid overfitting. However, labeled training data for real-world applications such as healthcare is limited and difficult to…

Text-to-image diffusion models are pushing the boundaries of what generative AI can achieve in our lives. Beyond their ability to generate general images, new personalization techniques have been proposed to customize the pre-trained base…

Image generation abilities of text-to-image diffusion models have significantly advanced, yielding highly photo-realistic images from descriptive text and increasing the viability of leveraging synthetic images to train computer vision…

While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently…

In recent years, diffusion models have gained popularity for their ability to generate higher-quality images in comparison to GAN models. However, like any other large generative models, these models require a huge amount of data,…

Modern machine learning models heavily rely on large datasets that often include sensitive and private information, raising serious privacy concerns. Differentially private (DP) data generation offers a solution by creating synthetic…

Diffusion models can generate realistic and diverse images, potentially facilitating data availability for data-intensive perception tasks. However, leveraging these models to boost performance on downstream tasks with synthetic data poses…

Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during…

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…

The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor. Compared to conventional Data Augmentation (DA) techniques (e.g. cropping and rotation), exploiting prevailing diffusion models for data…

Deep Generative Models (DGMs) have been shown to be powerful tools for generating tabular data, as they have been increasingly able to capture the complex distributions that characterize them. However, to generate realistic synthetic data,…