轻量语义分割新范式，兼顾精度与效率
LeMoRe: Learn More Details for Lightweight Semantic Segmentation
- 显式坐标方向+隐式中间表征协同建模
- 在多个数据集上实现高精度低计算量
- 适合资源受限场景的实时语义分割
轻量级语义分割对众多下游视觉任务至关重要。然而，现有方法常因特征建模复杂性难以平衡效率与性能。许多方法受限于固定架构和隐式表征学习，通常具有参数密集的设计，并依赖计算量大的视觉变换器框架。本文提出一种高效范式，通过显式与隐式建模的协同，在计算效率与表征保真度之间取得良好平衡。方法结合明确的笛卡尔方向与显式建模视角，以及隐式推断的中间表示，利用嵌套注意力机制高效捕捉全局依赖。在ADE20K、CityScapes、Pascal Context和COCO-Stuff等挑战性数据集上的大量实验表明，LeMoRe在性能与效率间实现了有效权衡。
原文摘要 · Abstract (English)
Lightweight semantic segmentation is essential for many downstream vision tasks. Unfortunately, existing methods often struggle to balance efficiency and performance due to the complexity of feature modeling. Many of these existing approaches are constrained by rigid architectures and implicit representation learning, often characterized by parameter-heavy designs and a reliance on computationally intensive Vision Transformer-based frameworks. In this work, we introduce an efficient paradigm by synergizing explicit and implicit modeling to balance computational efficiency with representational fidelity. Our method combines well-defined Cartesian directions with explicitly modeled views and implicitly inferred intermediate representations, efficiently capturing global dependencies through a nested attention mechanism. Extensive experiments on challenging datasets, including ADE20K, CityScapes, Pascal Context, and COCO-Stuff, demonstrate that LeMoRe strikes an effective balance between performance and efficiency.
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。