Abstract: Recently graph auto-encoders have received increasingly widespread attention as one of the important models in the field of deep learning. Existing graph auto-encoder models only use graph ...

Abstract: Change detection is a critical task in earth observation applications. Recently, deep-learning-based methods have shown promising performance and are quickly adopted in change detection.

We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...