arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.07151cs.CV
收藏

严重类别不平衡下的多类分割:顶板损伤评估实例研究

Multi-class segmentation under severe class imbalance: A case study in roof damage assessment

CrowdAI

Jean-Baptiste Boin, Nat Roth, Jigar Doshi, Pablo Llueca, Nicolas Borensztein

摘要:

屋顶损坏分类和分割的任务,从开销图像提出了独特的挑战。在这项工作中,我们选择解决由于强烈的阶级不平衡所带来的挑战。我们提出了四种不同的技术,旨在减轻这个问题。通过一个新的方案,通过对少数类进行过采样将数据馈送到网络,以及其他三个网络架构改进,我们设法将模型的宏观平均F1分数提高了39.9个百分点,从而提高了分割性能,特别是在少数类上。

英文摘要:

The task of roof damage classification and segmentation from overhead imagery presents unique challenges. In this work we choose to address the challenge posed due to strong class imbalance. We propose four distinct techniques that aim at mitigating this problem. Through a new scheme that feeds the data to the network by oversampling the minority classes, and three other network architectural improvements, we manage to boost the macro-averaged F1-score of a model by 39.9 percentage points, thus achieving improved segmentation performance, especially on the minority classes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑