聚焦难区分区域，用轻量设计提升分割效率与精度。
FoR-Net: Learning to Focus on Hard Regions for Efficient Semantic Segmentation
- 通过重要性图与Top-K机制，动态关注难分区域如细长结构和边界。
- 在有限算力下，城市景观数据集上达到媲美复杂模型的分割性能。
- 适合资源受限场景，为高效语义分割提供新思路。
我们提出FoR-Net，一种高效的语义分割框架，专注于识别并增强困难区域。不同于依赖重型全局建模的方法，FoR-Net采用轻量策略，通过学习的重要性图和Top-K激活机制，选择性地强化信息丰富的区域。具体而言，选择器模块预测区域重要性，使模型能聚焦于细长结构、物体边界等挑战性区域。利用具有不同感受野的卷积分支实现多尺度推理，支持多样化的空间上下文聚合。我们在计算资源受限条件下，在Cityscapes基准上评估了FoR-Net。尽管设计轻量且使用标准训练配置，其仍展现出具有竞争力的性能，并对困难区域表现出更强的关注。结果表明，选择性区域聚焦推理可作为语义分割的一种实用且高效替代方案。本工作探索了资源受限下的区域聚焦推理，为构建高效且区域感知的分割模型提供了新见解。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。