人工智能
合成数据
计算机科学
机器学习
深度学习
水准点(测量)
降噪
可靠性(半导体)
监督学习
合成孔径雷达
噪音(视频)
人工神经网络
干涉合成孔径雷达
数据建模
模式识别(心理学)
训练集
滤波器(信号处理)
还原(数学)
培训(气象学)
实验数据
标记数据
特征(语言学)
数据挖掘
一般化
噪声数据
特征学习
作者
Kang Liang,Zhong Lu,Jin‐Woo Kim
标识
DOI:10.1109/tgrs.2026.3697799
摘要
Deep learning is revolutionizing the way InSAR data are processed. Supervised deep learning models trained on synthetic datasets have demonstrated strong performance according to conventional evaluation metrics. However, in practice, many supervised InSAR phase denoising filters tend to oversmooth fringe patterns and generate ghost fringes in decorrelated regions, raising concerns about the reliability of models trained solely on synthetic data in real-world applications. In this work, we introduce Noise2Fringe, an unsupervised learning framework that enables the direct training of denoising filters on noisy interferograms, eliminating the need for clean references, while achieving performance comparable to that of supervised models. This framework allows a fair comparison between models trained exclusively on real versus synthetic data, independent of the training scheme. On synthetic benchmarks, models trained on real data appear to underperform compared to those trained on synthetic data. However, in real-world interferograms, the opposite holds: synthetic-trained models oversmooth and generate ghost fringes, whereas real-trained models avoid these artifacts. These findings reveal (i) a much larger gap between synthetic and real data than previously assumed, (ii) an overestimation of the effectiveness of synthetic-trained models, and (iii) deficiencies in current evaluation methods that rely heavily on simulated benchmarks. We further find that incorporating auxiliary information, such as the Amplitude Dispersion Index, into the input can enhance denoising performance. Overall, this study demonstrates that models trained solely on synthetic data may be far less reliable in real-world applications than suggested by their benchmark results, and emphasizes that generating more realistic training datasets should take precedence over designing increasingly complex model architectures.
科研通智能强力驱动
Strongly Powered by AbleSci AI