Related papers: Classifier-Free Guidance inside the Attraction Bas…

Knowledge Distillation is an effective method to transfer the learning across deep neural networks. Typically, the dataset originally used for training the Teacher model is chosen as the "Transfer Set" to conduct the knowledge transfer to…

We study the memorization and generalization capabilities of Diffusion Models (DMs) when data lies on a structured latent manifold. Specifically, we consider a set of $P$ data points in $N$ dimensions confined to a latent subspace of…

Imperfect score-matching leads to a shift between the training and the sampling distribution of diffusion models. Due to the recursive nature of the generation process, errors in previous steps yield sampling iterates that drift away from…

Due to the domain gap between real-world and synthetic hazy images, current data-driven dehazing algorithms trained on synthetic datasets perform well on synthetic data but struggle to generalize to real-world scenarios. To address this…

Studying data memorization in neural language models helps us understand the risks (e.g., to privacy or copyright) associated with models regurgitating training data and aids in the development of countermeasures. Many prior works -- and…

Text-to-image diffusion models have proven effective for solving many image editing tasks. However, the seemingly straightforward task of seamlessly relocating objects within a scene remains surprisingly challenging. Existing methods…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Recent advances in generative diffusion models have shown a notable inherent understanding of image style and semantics. In this paper, we leverage the self-attention features from pretrained diffusion networks to transfer the visual…

Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, such as classifier…

With the rapid development of text-to-vision generation diffusion models, classifier-free guidance has emerged as the most prevalent method for conditioning. However, this approach inherently requires twice as many steps for model…

Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regenerating the entire image; 2) guidance solely by a reference…

Video-based action recognition is one of the most popular topics in computer vision. With recent advances of selfsupervised video representation learning approaches, action recognition usually follows a two-stage training framework, i.e.,…

Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classifier to provide conditional gradient guidance at each time…

With the great success of diffusion models in image generation, diffusion-based image compression is attracting increasing interests. However, due to the random noise introduced in the diffusion learning, they usually produce…

Tabular data generation has attracted significant research interest in recent years, with the tabular diffusion models greatly improving the quality of synthetic data. However, while memorization, where models inadvertently replicate exact…

Recent advancements in diffusion models revolutionize image generation but pose risks of misuse, such as replicating artworks or generating deepfakes. Existing image protection methods, though effective, struggle to balance protection…

Generative image models, since introduction, have become a global phenomenon. From new arts becoming possible to new vectors of abuse, many new capabilities have become available. One of the challenging issues with generative models is…

Over-parameterized deep neural networks are able to achieve excellent training accuracy while maintaining a small generalization error. It has also been found that they are able to fit arbitrary labels, and this behaviour is referred to as…

We propose self-diffusion, a novel framework for solving inverse problems without relying on pretrained generative models. Traditional diffusion-based approaches require training a model on a clean dataset to learn to reverse the forward…

Diffusion models trained on large datasets can synthesize photo-realistic images of remarkable quality and diversity. However, attributing these images back to the training data-that is, identifying specific training examples which caused…