Related papers: Detail Consistent Stage-Wise Distillation for Effi…

We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur…

Dataset Distillation (DD) aims to synthesize a small dataset capable of performing comparably to the original dataset. Despite the success of numerous DD methods, theoretical exploration of this area remains unaddressed. In this paper, we…

This paper proposes a novel method for depth completion, which leverages multi-view improved monitored distillation to generate more precise depth maps. Our approach builds upon the state-of-the-art ensemble distillation method, in which we…

Diffusion Probabilistic Models (DPMs) suffer from inefficient inference due to their slow sampling and high memory consumption, which limits their applicability to various medical imaging applications. In this work, we propose a novel…

Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual…

In the realm of text-to-3D generation, utilizing 2D diffusion models through score distillation sampling (SDS) frequently leads to issues such as blurred appearances and multi-faced geometry, primarily due to the intrinsically noisy nature…

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

3D medical imaging is in high demand and essential for clinical diagnosis and scientific research. Currently, diffusion models (DMs) have become an effective tool for medical imaging reconstruction thanks to their ability to learn rich,…

Medical image segmentation faces challenges due to variations in anatomical structures. While convolutional neural networks (CNNs) effectively capture local features, they struggle with modeling long-range dependencies. Transformers…

Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the…

3D Gaussian Splatting (3DGS) has exhibited remarkable efficacy in novel view synthesis (NVS). However, it suffers from a significant drawback: achieving high-fidelity rendering typically necessitates a large number of 3D Gaussians,…

Leveraging the powerful capabilities of diffusion models has yielded quite effective results in medical image segmentation tasks. However, existing methods typically transfer the original training process directly without specific…

Dataset distillation or condensation aims to generate a smaller but representative subset from a large dataset, which allows a model to be trained more efficiently, meanwhile evaluating on the original testing data distribution to achieve…

Brain tumor segmentation remains a significant challenge, particularly in the context of multi-modal magnetic resonance imaging (MRI) where missing modality images are common in clinical settings, leading to reduced segmentation accuracy.…

For 3D medical image (e.g. CT and MRI) segmentation, the difficulty of segmenting each slice in a clinical case varies greatly. Previous research on volumetric medical image segmentation in a slice-by-slice manner conventionally use the…

Recent advancements in human image animation have been propelled by video diffusion models, yet their reliance on numerous iterative denoising steps results in high inference costs and slow speeds. An intuitive solution involves adopting…

Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis. However, existing methods typically rely on Score Distillation Sampling (SDS) loss, which involves asymmetric KL divergence--a…

Based on the Denoising Diffusion Probabilistic Model (DDPM), medical image segmentation can be described as a conditional image generation task, which allows to compute pixel-wise uncertainty maps of the segmentation and allows an implicit…

Distilling latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face two critical challenges: (1) They hinge on long training using a huge…

Automated segmentation in medical image analysis is a challenging task that requires a large amount of manually labeled data. However, most existing learning-based approaches usually suffer from limited manually annotated medical data,…