Abstract:We present FoR-Net, an efficient semantic segmentation framework 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. Multi-scale reasoning is achieved using convolutional branches with different receptive fields, allowing diverse spatial context aggregation. We evaluate FoR-Net on the Cityscapes benchmark under limited computational resources. Despite its efficient design and standard training configuration, FoR-Net achieves competitive performance and exhibits improved attention to difficult regions. These results suggest that selective region-focused reasoning can serve as a practical and efficient alternative for semantic segmentation. This work explores region-focused reasoning under resource-constrained settings and provides insights for developing efficient and region-aware segmentation models.
| Comments: | 9 pages, 2 figures, 2 tables. Efficient semantic segmentation under resource-constrained settings. Code will be released |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| ACM classes: | I.2.10 |
| Cite as: | arXiv:2605.02764 [cs.CV] |
| (or arXiv:2605.02764v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02764 arXiv-issued DOI via DataCite |
From: Sheng Wei Chan [view email]
[v1]
Mon, 4 May 2026 16:05:37 UTC (542 KB)
[v2]
Mon, 25 May 2026 10:36:40 UTC (547 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。