轻量语义分割模型通过特征精炼模块提升精度与效率平衡。
A feature refinement module for light-weight semantic segmentation network
- 引入特征精炼模块，融合多阶段特征与非局部上下文信息。
- 在Cityscapes上达80.4% mIoU，仅需214.82 GFLOPs。
- 适合资源受限场景下的实时高精度语义分割应用。
低计算复杂度与高分割精度对实际语义分割任务至关重要。然而，为加速推理，现有方法多采用参数极少的轻量网络，导致表征能力下降，精度显著降低。为此，本文提出一种新型语义分割方法，提升轻量网络获取语义信息的能力。具体地，设计特征精炼模块（FRM），从骨干网络生成的多阶段特征图中提取语义，并利用Transformer块捕捉非局部上下文信息。在Cityscapes和Bdd100K数据集上的实验表明，该方法在精度与计算成本间实现良好权衡，尤其在Cityscapes测试集上达到80.4% mIoU，仅需214.82 GFLOPs。
原文摘要 · Abstract (English)
Low computational complexity and high segmentation accuracy are both essential to the real-world semantic segmentation tasks. However, to speed up the model inference, most existing approaches tend to design light-weight networks with a very limited number of parameters, leading to a considerable degradation in accuracy due to the decrease of the representation ability of the networks. To solve the problem, this paper proposes a novel semantic segmentation method to improve the capacity of obtaining semantic information for the light-weight network. Specifically, a feature refinement module (FRM) is proposed to extract semantics from multi-stage feature maps generated by the backbone and capture non-local contextual information by utilizing a transformer block. On Cityscapes and Bdd100K datasets, the experimental results demonstrate that the proposed method achieves a promising trade-off between accuracy and computational cost, especially for Cityscapes test set where 80.4% mIoU is achieved and only 214.82 GFLOPs are required.
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。