Our approach adopts the pre-trained model as the base code/query encoder and optimizes it using multimodal contrastive learning and soft data augmentation. CoCoSoDa is comprised of the following four ...
This repository is the official implementation of the paper RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models, developed based on the OpenMMLab codebase. The ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results