FoR-Net: Focus-on-Regions Network for Semantic Segmentation

Abstract

This paper presents Focus-on-Regions Network (FoR-Net), an efficient semantic segmentation framework that explicitly focuses on hard regions through a selector-driven Top-K mechanism. Instead of relying on heavy global modeling, FoR-Net selectively enhances structurally informative regions. Multi-scale reasoning branches are introduced to aggregate spatial context efficiently. Experiments on the Cityscapes dataset demonstrate that FoR-Net achieves competitive performance while maintaining a lightweight architecture.

arXiv comment4 pages, 2 figures. Accepted to the 2026 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2026)