.png){kind=icon}
返回
GCD-DDPM: A Generative Change Detection Model Based on Difference-Feature-Guided DDPM
.png){kind=icon}
OA
AI
DOI：10.1109/TGRS.2024.3381752.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning (DL)-based methods have recently shown great promise in bitemporal change detection (CD). Existing discriminative methods based on convolutional neural networks (CNNs) and Transformers rely on discriminative representation learning for change recognition while struggling with exploring local and long-range contextual dependencies. As a result, it is still challenging to obtain fine-grained and robust CD maps in diverse ground scenes. To cope with this challenge, this work proposes a generative CD model called GCD-DDPM to directly generate CD maps by exploiting the denoising diffusion probabilistic model (DDPM), instead of classifying each pixel into changed or unchanged categories. Furthermore, the difference conditional encoder (DCE), is designed to guide the generation of CD maps by exploiting multilevel difference features. Leveraging the variational inference (VI) procedure, GCD-DDPM can adaptively recalibrate the CD results through an iterative inference process, while accurately distinguishing subtle and irregular changes in diverse scenes. Finally, a noise suppression-based semantic enhancer (NSSE) is specifically designed to mitigate noise in the current step's change-aware feature representations from the CD Encoder. This refinement, serving as an attention map, can guide subsequent iterations while enhancing CD accuracy. Extensive experiments on four high-resolution CD datasets (CDD) confirm the superior performance of the proposed GCD-DDPM. The code for this work will be available at https://github.com/udrs/GCD.
Keyword:
Feature extraction
Transformers
Adaptation models
Task analysis
Semantics
Probabilistic logic
Data models
Change detection (CD)
denoising diffusion probabilistic model (DDPM)
generative models
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
SRDiff: Single image super-resolution with diffusion probabilistic modelsSRDiff: 具有扩散概率模型的单幅图像超分辨率.png)
NEUROCOMPUTING
OAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏SpectralDiff: A Generative Framework for Hyperspectral Image Classification With Diffusion ModelsOAAI
OAAI分享收藏Sensorless Control of Z Source Inverter fed BLDC Motor Drive by FOC - DTC Hybrid Control Strategy Using Fuzzy Logic Controller采用模糊逻辑控制器的foc-dtc混合控制策略的Z源逆变器馈电BLDC电机驱动的无传感器控制
PREAI
分享收藏Change Detection Based on Deep Siamese Convolutional Network for Optical Aerial Images基于深度暹罗卷积网络的光学航空影像变化检测
PREAI
分享收藏SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR ImagesSnunet-cd: 一个用于VHR图像变化检测的密集连体网络
PREAI
分享收藏分享收藏
查看更多内容