Masked Angle-Aware Autoencoder for Remote Sensing Images
This work addresses the need for rotation-invariant representations in remote sensing image analysis, offering a domain-specific incremental improvement.
The paper tackled the problem of domain gap and overlooked angle diversity in remote sensing images by proposing the Masked Angle-Aware Autoencoder (MA3E), which achieved more competitive performance than existing methods on seven datasets across three downstream tasks.
To overcome the inherent domain gap between remote sensing (RS) images and natural images, some self-supervised representation learning methods have made promising progress. However, they have overlooked the diverse angles present in RS objects. This paper proposes the Masked Angle-Aware Autoencoder (MA3E) to perceive and learn angles during pre-training. We design a \textit{scaling center crop} operation to create the rotated crop with random orientation on each original image, introducing the explicit angle variation. MA3E inputs this composite image while reconstruct the original image, aiming to effectively learn rotation-invariant representations by restoring the angle variation introduced on the rotated crop. To avoid biases caused by directly reconstructing the rotated crop, we propose an Optimal Transport (OT) loss that automatically assigns similar original image patches to each rotated crop patch for reconstruction. MA3E demonstrates more competitive performance than existing pre-training methods on seven different RS image datasets in three downstream tasks.