返回
Diff-HRNet: A Diffusion Model-Based High-Resolution Network for Remote Sensing Semantic Segmentation
DOI:10.1109/LGRS.2024.3505552.png)
摘要
En 中文
The semantic segmentation methods based on deep neural networks predominantly employ supervised learning, relying heavily on the quantity and quality of annotated samples. Due to the complexity of high-resolution remote sensing imagery, obtaining sufficient and precise pixel-level labeled data is highly challenging. This letter introduces a novel self-supervised learning method using a pretrained denoising diffusion probabilistic model (DDPM) to leverage semantic information from large-scale unlabeled remote sensing imageries. Building on this, a multistage fusion scheme between pretrained features and high-resolution features is proposed, enabling the network to learn more effective strategies to leverage prior information provided by the pretrained model while preserving the rich semantic details of high-resolution images. Experimental results on two remote sensing semantic segmentation datasets show that the proposed Diff-HRNet outperforms all compared methods, demonstrating the potential of pretrained diffusion models in extracting crucial feature representations for semantic segmentation tasks.
Keyword:
Feature extraction
Remote sensing
Semantics
Spatial resolution
Diffusion models
Noise reduction
Noise measurement
Convolution
Supervised learning
Denoising diffusion probabilistic model (DDPM)
self-supervised learning
semantic segmentation
semantic segmentation
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
暂无机构信息
引用论文
RS-Dseg: semantic segmentation of high-resolution remote sensing images based on a diffusion model component with unsupervised pretrainingRs-dseg: 基于无监督预训练扩散模型成分的高分辨率遥感影像语义分割
SCIENTIFIC REPORTS
IF3.9
Renal Tubular Secretion of Tanshinol: Molecular Mechanisms, Impact on Its Systemic Exposure, and Propensity for Dose-Related Nephrotoxicity and for Renal Herb-Drug Interactions丹参素的肾小管分泌: 分子机制,对其全身暴露的影响以及剂量相关的肾毒性和肾草药相互作用的倾向

