Abstract: This paper addresses few-shot semantic segmentation (FSS) guided by text, where we classify unseen novel classes using image and text references as in-context examples, without the need for ...

Abstract: The complexity of geospatial data and target variability in remote sensing imagery challenge semantic segmentation. To accurately segment dense targets, enhance feature distinguishability, ...

Click for full abstract Advanced diffusion models like RPG, Stable Diffusion 3 and FLUX have made notable strides in compositional text-to-image generation. However, these methods typically exhibit ...

Semantic segmentation of remote sensing images is pivotal for comprehensive Earth observation, but the demand for interpreting new object categories, coupled with the high expense of manual annotation ...