通过双层扰动一致性提升遥感变化检测的无监督数据利用效率
GTPC-SSCD: Gate-guided Two-level Perturbation Consistency-based Semi-Supervised Change Detection
- 在图像和特征两层设计扰动一致性，增强未标注数据利用
- 在六个基准数据集上优于7种前沿方法，最高提升3.2个百分点
- 基于样本难易度自适应开启扰动，适合遥感图像变化检测任务
半监督变化检测（SSCD）利用部分标注数据与大量未标注数据，识别多时相遥感影像间的差异。现有基于一致性正则的方法主要在单一层次进行扰动，限制了未标注数据的利用效率，未能充分挖掘其潜力。本文提出一种新型门控双层扰动一致性半监督变化检测方法（GTPC-SSCD），同时在图像层面保持强-弱一致性，在特征层面维持扰动一致性，提升了未标注数据的利用效率。此外，设计了一种基于难易度分析的门控机制，评估不同样本的训练复杂度，决定是否对每个样本进行特征扰动。通过差异化处理，网络能更高效地挖掘未标注数据的潜力。在六个基准变化检测数据集上的大量实验表明，GTPC-SSCD优于七种前沿方法。
原文摘要 · Abstract (English)
Semi-supervised change detection (SSCD) utilizes partially labeled data and abundant unlabeled data to detect differences between multi-temporal remote sensing images. The mainstream SSCD methods based on consistency regularization have limitations. They perform perturbations mainly at a single level, restricting the utilization of unlabeled data and failing to fully tap its potential. In this paper, we introduce a novel Gate-guided Two-level Perturbation Consistency regularization-based SSCD method (GTPC-SSCD). It simultaneously maintains strong-to-weak consistency at the image level and perturbation consistency at the feature level, enhancing the utilization efficiency of unlabeled data. Moreover, we develop a hardness analysis-based gating mechanism to assess the training complexity of different samples and determine the necessity of performing feature perturbations for each sample. Through this differential treatment, the network can explore the potential of unlabeled data more efficiently. Extensive experiments conducted on six benchmark CD datasets demonstrate the superiority of our GTPC-SSCD over seven state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。