轻量级云图分割模型SCANet，实时高效且精度领先。
Segregation and Context Aggregation Network for Real-time Cloud Segmentation
- 分离与上下文聚合模块分别处理天空与云特征
- SCANet-lite仅90K参数，达1390帧/秒，远超实时
- 无需ImageNet预训练也能提升性能，适合边缘设备
从强度图像中进行云分割是大气科学和计算机视觉中的关键任务，有助于天气预报和气候分析。地面观测的云图分割旨在从图像中提取云信息以进行后续特征分析。现有方法难以在分割精度与计算效率之间取得平衡，限制了其在边缘设备上的实际部署。为此，我们提出SCANet，一种新型轻量级云分割模型，包含分离与上下文聚合模块（SCAM），将粗略分割图细化为加权的天空与云特征并分别处理。SCANet实现当前最佳性能的同时大幅降低计算复杂度：SCANet-large（429万参数）达到与顶尖方法相当的精度，参数量减少70.9%；SCANet-lite（9万参数）在FP16下达到1390帧/秒，远超实时标准。此外，我们提出一种高效的预训练策略，在无ImageNet预训练的情况下仍可显著提升性能。
原文摘要 · Abstract (English)
Cloud segmentation from intensity images is a pivotal task in atmospheric science and computer vision, aiding weather forecasting and climate analysis. Ground-based sky/cloud segmentation extracts clouds from images for further feature analysis. Existing methods struggle to balance segmentation accuracy and computational efficiency, limiting real-world deployment on edge devices, so we introduce SCANet, a novel lightweight cloud segmentation model featuring Segregation and Context Aggregation Module (SCAM), which refines rough segmentation maps into weighted sky and cloud features processed separately. SCANet achieves state-of-the-art performance while drastically reducing computational complexity. SCANet-large (4.29M) achieves comparable accuracy to state-of-the-art methods with 70.9% fewer parameters. Meanwhile, SCANet-lite (90K) delivers 1390 fps in FP16, surpassing real-time standards. Additionally, we propose an efficient pre-training strategy that enhances performance even without ImageNet pre-training.
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。