中文
相关论文

相关论文: SD-FSMIS: Adapting Stable Diffusion for Few-Shot M…

200 篇论文

This paper presents DFR (Decompose, Fuse and Reconstruct), a novel framework that addresses the fundamental challenge of effectively utilizing multi-modal guidance in few-shot segmentation (FSS). While existing approaches primarily rely on…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Shuai Chen , Fanman Meng , Xiwei Zhang , Haoran Wei , Chenhao Wu , Qingbo Wu , Hongliang Li

Cross-domain Few-shot Medical Image Segmentation (CD-FSMIS) is a potential solution for segmenting medical images with limited annotation using knowledge from other domains. The significant performance of current CD-FSMIS models relies on…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Yazhou Zhu , Haofeng Zhang

Current semantic segmentation models typically require a substantial amount of manually annotated data, a process that is both time-consuming and resource-intensive. Alternatively, leveraging advanced text-to-image models such as Midjourney…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Bo Gao , Jianhui Wang , Xinyuan Song , Yangfan He , Fangxu Xing , Tianyu Shi

Diffusion models have proven to be highly effective in generating high-quality images. However, adapting large pre-trained diffusion models to new domains remains an open challenge, which is critical for real-world applications. This paper…

计算机视觉与模式识别 · 计算机科学 2023-07-28 Enze Xie , Lewei Yao , Han Shi , Zhili Liu , Daquan Zhou , Zhaoqiang Liu , Jiawei Li , Zhenguo Li

Diffusion models have recently received increasing research attention for their remarkable transfer abilities in semantic segmentation tasks. However, generating fine-grained segmentation masks with diffusion models often requires…

计算机视觉与模式识别 · 计算机科学 2024-01-23 Koichi Namekata , Amirmojtaba Sabour , Sanja Fidler , Seung Wook Kim

Solving medical imaging data scarcity through semantic image generation has attracted growing attention in recent years. However, existing generative models mainly focus on synthesizing whole-organ or large-tissue structures, showing…

图像与视频处理 · 电气工程与系统科学 2025-12-19 Jiahao Xia , Yutao Hu , Yaolei Qi , Zhenliang Li , Wenqi Shao , Junjun He , Ying Fu , Longjiang Zhang , Guanyu Yang

Multimodal medical images play a crucial role in the precise and comprehensive clinical diagnosis. Diffusion model is a powerful strategy to synthesize the required medical images. However, existing approaches still suffer from the problem…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Jiahua Xu , Dawei Zhou , Lei Hu , Zaiyi Liu , Nannan Wang , Xinbo Gao

Objective: Cone-beam computed tomography (CBCT) provides a low-dose imaging alternative to conventional CT, but suffers from noise, scatter, and artifacts that degrade image quality. Synthetic CT (sCT) aims to translate CBCT to high-quality…

医学物理 · 物理学 2025-09-23 Alzahra Altalib , Chunhui Li , Alessandro Perelli

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,…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Chenhe Du , Qing Wu , Xuanyu Tian , Jingyi Yu , Hongjiang Wei , Yuyao Zhang

Despite deep convolutional neural networks achieved impressive progress in medical image computing and analysis, its paradigm of supervised learning demands a large number of annotations for training to avoid overfitting and achieving…

计算机视觉与模式识别 · 计算机科学 2020-12-11 Liyan Sun , Chenxin Li , Xinghao Ding , Yue Huang , Guisheng Wang , Yizhou Yu

The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling steps, such…

Weakly supervised medical image segmentation (MIS) using generative models is crucial for clinical diagnosis. However, the accuracy of the segmentation results is often limited by insufficient supervision and the complex nature of medical…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Zhihao Shuai , Yinan Chen , Shunqiang Mao , Yihan Zho , Xiaohong Zhang

Diffusion models have achieved significant success in both natural image and medical image domains, encompassing a wide range of applications. Previous investigations in medical images have often been constrained to specific anatomical…

计算机视觉与模式识别 · 计算机科学 2025-12-08 Yongrui Yu , Yannian Gu , Shaoting Zhang , Xiaofan Zhang

As a technique to alleviate the pressure of data annotation, semi-supervised learning (SSL) has attracted widespread attention. In the specific domain of medical image segmentation, semi-supervised methods (SSMIS) have become a research…

计算机视觉与模式识别 · 计算机科学 2024-11-20 Bingli Wang , Houcheng Su , Nan Yin , Mengzhu Wang , Li Shen

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

计算机视觉与模式识别 · 计算机科学 2024-08-30 Ali Hatamizadeh , Jiaming Song , Guilin Liu , Jan Kautz , Arash Vahdat

Multi-modal images play a crucial role in comprehensive evaluations in medical image analysis providing complementary information for identifying clinically important biomarkers. However, in clinical practice, acquiring multiple modalities…

图像与视频处理 · 电气工程与系统科学 2024-10-02 Jonghun Kim , Hyunjin Park

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…

计算机视觉与模式识别 · 计算机科学 2025-03-03 Qianlong Xiang , Miao Zhang , Yuzhang Shang , Jianlong Wu , Yan Yan , Liqiang Nie

Unsupervised deformable image registration is one of the challenging tasks in medical imaging. Obtaining a high-quality deformation field while preserving deformation topology remains demanding amid a series of deep-learning-based…

计算机视觉与模式识别 · 计算机科学 2023-07-25 Yi Qin , Xiaomeng Li

Few-Shot Segmentation (FSS) aims to segment novel classes using only a few annotated images. Despite considerable progress under pixel-wise support annotation, current FSS methods still face three issues: the inflexibility of backbone…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Shuai Chen , Fanman Meng , Chenhao Wu , Haoran Wei , Runtong Zhang , Qingbo Wu , Linfeng Xu , Hongliang Li

While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Zihua Liu , Yizhou Li , Songyan Zhang , Masatoshi Okutomi