Urban Change Detection Using a Dual-Task Siamese Network and Semi-Supervised Learning
This work addresses urban monitoring for applications like planning, but it is incremental as it builds on existing SSL and network architectures.
The study tackled urban change detection from bi-temporal image pairs by proposing a semi-supervised learning method with a dual-task Siamese network, achieving improved results compared to fully supervised benchmarks on the SpaceNet7 dataset.
In this study, a Semi-Supervised Learning (SSL) method for improving urban change detection from bi-temporal image pairs was presented. The proposed method adapted a Dual-Task Siamese Difference network that not only predicts changes with the difference decoder, but also segments buildings for both images with a semantics decoder. First, the architecture was modified to produce a second change prediction derived from the semantics predictions. Second, SSL was adopted to improve supervised change detection. For unlabeled data, we introduced a loss that encourages the network to predict consistent changes across the two change outputs. The proposed method was tested on urban change detection using the SpaceNet7 dataset. SSL achieved improved results compared to three fully supervised benchmarks.