Abstract: Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models. To leverage the ...

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 ...

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.

This project uses UV for dependency management. Krippendorff's alpha is more meaningful for larger data samples, however low agreement can still be a sign of labeling issue. The code requires at least ...