FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation

ArXi:2605.02764v1 Announce Type: new We present FoR-Net, a lightweight architecture for semantic segmentation that focuses on identifying and enhancing hard regions. Instead of relying on heavy global modeling, FoR-Net adopts an efficient strategy that selectively emphasizes informative regions through a learned importance map and a Top-K activation mechanism. Specifically, a selector module predicts region-wise importance, enabling the model to focus on challenging areas such as thin structures and object boundaries.