Self-supervised Domain-agnostic Domain Adaptation for Satellite Images
This addresses domain adaptation challenges for satellite image analysis, particularly in large-scale multi-temporal and multi-sensory scenarios, though it appears incremental as it builds on existing domain adaptation concepts.
The paper tackles the problem of domain shift in satellite image processing by proposing a self-supervised domain-agnostic domain adaptation method that eliminates the need for explicit domain definitions, achieving improved generalizability as verified on public benchmarks.
Domain shift caused by, e.g., different geographical regions or acquisition conditions is a common issue in machine learning for global scale satellite image processing. A promising method to address this problem is domain adaptation, where the training and the testing datasets are split into two or multiple domains according to their distributions, and an adaptation method is applied to improve the generalizability of the model on the testing dataset. However, defining the domain to which each satellite image belongs is not trivial, especially under large-scale multi-temporal and multi-sensory scenarios, where a single image mosaic could be generated from multiple data sources. In this paper, we propose an self-supervised domain-agnostic domain adaptation (SS(DA)2) method to perform domain adaptation without such a domain definition. To achieve this, we first design a contrastive generative adversarial loss to train a generative network to perform image-to-image translation between any two satellite image patches. Then, we improve the generalizability of the downstream models by augmenting the training data with different testing spectral characteristics. The experimental results on public benchmarks verify the effectiveness of SS(DA)2.