用自监督学习检测雷达影像中的异常变化,精度显著优于传统方法。
T-SAR-JEPA: Self-Supervised Temporal Anomaly Detection in SAR Amplitude Stacks via Latent Prediction

- 通过预测时序潜空间实现无监督异常检测,仅依赖强度数据。
- 在夏威夷火山事件中达到77.0%的ROC-AUC,远超基准方法(约50%)。
- 适用于遥感监测场景,适合关注地表变化的科研与应用人员。
我们提出T-SAR-JEPA,一种基于潜空间预测的自监督时序异常检测框架,用于合成孔径雷达(SAR)幅度序列分析。采用来自SAR-JEPA的ViT-Base/16编码器,在39,300个Capella图像块上通过局部掩码重建与梯度特征预测进行领域适应。一个带正弦时间编码的时序变换器,从K=7次观测中预测未来潜状态,渐进解冻策略显著降低验证损失。模型仅使用幅度信息;干涉相干性仅作为独立伪真值。在DFC 2026数据集(300条时序,三个感兴趣区)上,对夏威夷喷发窗口的检测达到77.0%的ROC-AUC,优于RX、PaDiM、Linear AR和LSTM基线(约50%)。空间相干性达99.9%(p < 0.001,置换检验),证实检测结果具有结构合理性。代码见:https://github.com/TerraLatent/t-sar-jepa。
原文摘要 · Abstract (English)
We present T-SAR-JEPA, a self-supervised framework for temporal anomaly detection in SAR amplitude stacks via latent prediction. A ViT-Base/16 encoder from SAR-JEPA is domain-adapted on 39,300 Capella patches using local masked reconstruction with gradient feature prediction. A temporal transformer with sinusoidal time encoding forecasts future latent states from K=7 acquisitions, with progressive unfreezing substantially reducing validation loss. The model operates on amplitude alone; InSAR coherence serves exclusively as independent pseudo-ground-truth. On the DFC 2026 dataset (300 time-series, three AOIs), T-SAR-JEPA achieves ROC-AUC of 77.0% on the Hawaii eruption window, outperforming RX, PaDiM, Linear AR, and LSTM baselines (~50%). Spatial coherence of 99.9% (p < 0.001, permutation test) confirms structured detections. Code: https://github.com/TerraLatent/t-sar-jepa
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。