.png){kind=icon}
返回
Robust Instance-Based Semi-Supervised Learning Change Detection for Remote Sensing Images
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3379223.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Semi-supervised change detection (SSCD) has experienced rapid development, with numerous semi-supervised methods being proposed to reduce the reliance on labeled data in change detection. Existing approaches typically rely on manually set high-confidence thresholds to select robust pseudolabels. However, the single-pixel threshold filtering method for pseudolabels (STFPs) lacks context correlation, cannot eliminate high-confidence false positive (HFP) samples, and leads to erroneously filtering out low-confidence true positive (LTP) samples. To address this issue, we propose robust instance-based semi-supervised learning (RISL) change detection for remote sensing (RS) images. RISL evaluates the reliability of each instance object by linking the semantic information of the context, thereby generating robust pseudolabels. In RISL, first, a simple boundary trimming (BT) module as a preprocessing method for change prediction map is introduced. BT can effectively remove low-confidence false positive (LFP) samples while avoiding confusion in the category of instance objects, thereby improving the quality of instance objects. Then, we propose a reliable instance evaluation module (RIEM) to evaluate the reliability of each instance object. RIEM combines the semantic information of the entire instance and establishes correlations between sample contexts to determine the reliability of the instance, effectively eliminating high false positive samples. In addition, consistency regularization (CR) is integrated into RISL, and a new strategy suitable for RIEM is constructed. This strategy enhances the model's generalization ability by mining and hiding semantic information from different views of unlabeled data. Experimental results on the challenging WHU-CD, LEVIR-CD, and CDD-CD datasets show that the proposed method achieves 89.80%, 90.01%, and 87.56% $F1$ scores on labeled data with 5% distribution. RISL achieves state-of-the-art performance compared to other methods.
Keyword:
Instance-based
remote sensing (RS)
semi-supervised change detection (SSCD)
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
Tropical browses: contents of phenolic compounds, in vitro gas production and stoichiometric relationship between short chain fatty acid and in vitro gas production热带浏览: 酚类化合物的含量， 体外 气体产生以及短链脂肪酸与 体外 气体产生之间的化学计量关系
.png){kind=icon}
PREAI
分享收藏
分享收藏Integrating remote sensing and machine learning into environmental monitoring and assessment of land use change将遥感和机器学习集成到环境监测和土地利用变化评估中
PREAI
分享收藏CTMFNet: CNN and Transformer Multiscale Fusion Network of Remote Sensing Urban Scene ImageryCTMFNet: CNN和Transformer多尺度遥感城市场景影像融合网络
PREAI
分享收藏
Selective Adversarial Adaptation-Based Cross-Scene Change Detection Framework in Remote Sensing Images基于选择性对抗适应的遥感影像跨场景变化检测框架
PREAI
分享收藏SemiCDNet: A Semisupervised Convolutional Neural Network for Change Detection in High Resolution Remote-Sensing ImagesSemiCDNet: 一种用于高分辨率遥感图像变化检测的半监督卷积神经网络
PREAI
分享收藏
查看更多内容