摘要
深度学习算法在语义分割领域已经取得大量突破,对这些算法的性能评估应选择标准、通用、全面的度量指标,以保证评价的客观性和有效性。通过对当前语义分割评价指标和度量方法进行归纳分析,从像素标记准确性、深度估计误差度量、执行效率、内存占用、鲁棒性等方面进行了多角度阐述,尤其对广泛应用的F1分数、mIoU、mPA、Dice系数、Hausdorff距离等准确性指标进行了详细介绍,并总结了提高分割网络鲁棒性的方法,指出了语义分割实验的要求和当前分割质量评价存在的问题。
Deep learning has made major breakthroughs in the field of semantic segmentation.Standard,well-known and comprehensive metrics should be used to evaluate the performance of these algorithms to ensure objectivity and effective-ness of the evaluation.Through summary of the existing semantic segmentation evaluation metrics,this paper elaborates from some aspects,e.g.,pixel accuracy,depth estimation error metric,operation efficiency,memory demand and robust-ness.Especially,the widely used accuracy metrics such as F1 score,mIoU,mPA,Dice coefficient and Hausdorff distance are introduced in detail.In addition,this paper expounds the related research on the robustness and generalization.Further-more,this paper points out the requirements in the semantic segmentation experiment and the limitations of segmentation quality evaluation.
作者
于营
王春平
付强
寇人可
吴巍屹
刘天勇
YU Ying;WANG Chunping;FU Qiang;KOU Renke;WU Weiyi;LIU Tianyong(Department of Electronic and Optical Engineering,Shijiazhuang Campus,Army Engineering University of PLA,Shijiazhuang 050005,China;School of Information and Intelligent Engineering,University of Sanya,Sanya,Hainan 572022,China;Department of Equipment Command and Management,Shijiazhuang Campus,Army Engineering University of PLA,Shijiazhuang 050005,China;School of Earth Sciences,Northeast Petroleum University,Daqing,Heilongjiang 163319,China)
出处
《计算机工程与应用》
CSCD
北大核心
2023年第6期57-69,共13页
Computer Engineering and Applications
基金
海南省自然科学基金(621QN270)。
