Published in IEEE Geoscience and Remote Sensing Letters, 2025
This paper proposes a novel framework that leverages diffusion models to synthesize diverse remote sensing instances for improving few-shot object detection performance.
Published in IGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium, 2025
This paper proposes Control Copy-Paste, a controllable diffusion-based data augmentation method for few-shot object detection in optical remote sensing imagery.
Published in arXiv preprint arXiv:2505.12108, 2025
This paper proposes EarthSynth, a diffusion-based generative foundation model that synthesizes multi-category, cross-satellite labeled Earth observation data for downstream remote sensing image interpretation tasks.
Published in IEEE Transactions on Geoscience and Remote Sensing, 2024
This paper is about addressing the challenges of few-shot object detection in remote-sensing images.