针对破损道路低分辨率图像，提出新训练策略提升语义分割效果。
A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads
- 设计14次实验的增量训练策略，专门应对小物体和形状不规则问题。
- 在RTK和TAS500数据集上分别达到79.8和68.8的mIoU，刷新最优结果。
- 适用于新兴国家道路数据场景，尤其适合小目标与罕见类别的分割任务。
自动驾驶依赖良好道路，但巴西85%的道路存在损伤，而现有自动驾驶语义分割数据集多为高分辨率城市道路图像。针对新兴国家代表性数据集——包含低分辨率、维护差道路图像及损伤类别标注的场景，面临三大挑战：像素极少的物体、形状模糊的物体以及高度稀疏的类别。为此，本文提出性能增量策略（PISSS），通过14组训练实验提升模型表现。采用PISSS后，在Road Traversing Knowledge (RTK) 和 Technik Autonomer Systeme 500 (TAS500) 测试集上分别获得79.8和68.8的mIoU，达到当前最佳水平。同时，本文还分析了DeepLabV3+在小物体分割中的局限性。
原文摘要 · Abstract (English)
Autonomous driving needs good roads, but 85% of Brazilian roads have damages that deep learning models may not regard as most semantic segmentation datasets for autonomous driving are high-resolution images of well-maintained urban roads. A representative dataset for emerging countries consists of low-resolution images of poorly maintained roads and includes labels of damage classes; in this scenario, three challenges arise: objects with few pixels, objects with undefined shapes, and highly underrepresented classes. To tackle these challenges, this work proposes the Performance Increment Strategy for Semantic Segmentation (PISSS) as a methodology of 14 training experiments to boost performance. With PISSS, we reached state-of-the-art results of 79.8 and 68.8 mIoU on the Road Traversing Knowledge (RTK) and Technik Autonomer Systeme 500 (TAS500) test sets, respectively. Furthermore, we also offer an analysis of DeepLabV3+ pitfalls for small object segmentation.
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。