Related papers: FoundIR-v2: Optimizing Pre-Training Data Mixtures …
Training diffusion models requires large datasets. However, acquiring large volumes of high-quality data can be challenging, for example, collecting large numbers of high-resolution images and long videos. On the other hand, there are many…
User data confidentiality protection is becoming a rising challenge in the present deep learning research. Without access to data, conventional data-driven model compression faces a higher risk of performance degradation. Recently, some…
As foundational models reshape scientific discovery, a bottleneck persists in dynamical system reconstruction (DSR): the ability to learn across system hierarchies. Many meta-learning approaches have been applied successfully to single…
In this work, we address the limitations of denoising diffusion models (DDMs) in image restoration tasks, particularly the shape and color distortions that can compromise image quality. While DDMs have demonstrated a promising performance…
Diffusion models are able to generate photorealistic images in arbitrary scenes. However, when applying diffusion models to image translation, there exists a trade-off between maintaining spatial structure and high-quality content. Besides,…
Image classification systems often inherit biases from uneven group representation in training data. For example, in face datasets for hair color classification, blond hair may be disproportionately associated with females, reinforcing…
Bridge models in image restoration construct a diffusion process from degraded to clear images. However, existing methods typically require training a bridge model from scratch for each specific type of degradation, resulting in high…
Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the…
Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics. This makes them highly promising for image reconstruction, where the goal is to recover a…
Image restoration has experienced significant advancements due to the development of deep learning. Nevertheless, it encounters challenges related to ill-posed problems, resulting in deviations between single model predictions and…
Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an…
Mix-up is a key technique for consistency regularization-based semi-supervised learning methods, blending two or more images to generate strong-perturbed samples for strong-weak pseudo supervision. Existing mix-up operations are performed…
Diffusion-based text-to-image generation models trade latency for quality: small models are fast but generate lower-quality images, while large models produce better images but are slow. We present MoDM, a novel caching-based serving system…
Pre-trained diffusion models have enabled significant advancements in All-in-One Restoration (AiOR), offering improved perceptual quality and generalization. However, diffusion-based restoration methods primarily rely on fine-tuning or…
A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a…
Recently, text-to-image (T2I) editing has been greatly pushed forward by applying diffusion models. Despite the visual promise of the generated images, inconsistencies with the expected textual prompt remain prevalent. This paper aims to…
Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object…
Text-to-video (T2V) diffusion models have shown promising capabilities in synthesizing realistic videos from input text prompts. However, the input text description alone provides limited control over the precise objects movements and…
In recent years, numerous ideas have emerged for designing a mutually reinforcing mechanism or extra stages for the image fusion task, ignoring the inevitable gaps between different vision tasks and the computational burden. We argue that…
Discriminative classifiers have become a foundational tool in deep learning for medical imaging, excelling at learning separable features of complex data distributions. However, these models often need careful design, augmentation, and…