CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding
Published in IEEE Transactions on Geoscience and Remote Sensing, 2023
Recommended citation: Muhtar, D., Zhang, X., Xiao, P., Li, Z., & Gu, F. (2023). CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding. IEEE Transactions on Geoscience and Remote Sensing. https://arxiv.org/abs/2304.09670
Integrating contrast learning and masked image modeling to enhance self-supervised pre-trained representation learning. Pre-training on the large scale MillionAID dataset, showing SOTA performance across different remote sensing downstream tasks. (Outperform MAE, MoCo, SwAV, and SimMIM, etc.).