Abstract: Class-incremental semantic segmentation focuses on updating the segmentation model with only new-class samples. Catastrophic forgetting and background shift are the two prevalent challenges.

This package provides seamless integration of pre-trained image segmentation models from Ilastik into Python workflows, empowering users with efficient and intuitive image segmentation capabilities ...

Novel Framework: First segmentation paradigm built on a unified multimodal understanding-generation architecture, eliminating task-specific modules. SOTA without Extra Heads: Demonstrates unified ...

Abstract: Semantic segmentation of high-resolution remote sensing images (RSIs) remains challenging due to the degradation of high-frequency (HF) semantic cues during convolutional encoding and the ...