FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913160983740416 |
|---|---|
| author | Chan, Sheng-Wei Pan, Hsin-Jui Shen, Chun-Po Wang, Yung-Che Li, Meng-Qian Lin, Chia-Min Chiang, Jen-Shiun |
| author_facet | Chan, Sheng-Wei Pan, Hsin-Jui Shen, Chun-Po Wang, Yung-Che Li, Meng-Qian Lin, Chia-Min Chiang, Jen-Shiun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02764 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation Chan, Sheng-Wei Pan, Hsin-Jui Shen, Chun-Po Wang, Yung-Che Li, Meng-Qian Lin, Chia-Min Chiang, Jen-Shiun Computer Vision and Pattern Recognition I.2.10 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. |
| title | FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition I.2.10 |
| url | https://arxiv.org/abs/2605.02764 |