点云语义分割的细粒度指标

Zhuheng Lu, Ting Wu, Yuewei Dai, Weiqing Li, Zhiyong Su
{"title":"点云语义分割的细粒度指标","authors":"Zhuheng Lu, Ting Wu, Yuewei Dai, Weiqing Li, Zhiyong Su","doi":"arxiv-2407.21289","DOIUrl":null,"url":null,"abstract":"Two forms of imbalances are commonly observed in point cloud semantic\nsegmentation datasets: (1) category imbalances, where certain objects are more\nprevalent than others; and (2) size imbalances, where certain objects occupy\nmore points than others. Because of this, the majority of categories and large\nobjects are favored in the existing evaluation metrics. This paper suggests\nfine-grained mIoU and mAcc for a more thorough assessment of point cloud\nsegmentation algorithms in order to address these issues. Richer statistical\ninformation is provided for models and datasets by these fine-grained metrics,\nwhich also lessen the bias of current semantic segmentation metrics towards\nlarge objects. The proposed metrics are used to train and assess various\nsemantic segmentation algorithms on three distinct indoor and outdoor semantic\nsegmentation datasets.","PeriodicalId":501174,"journal":{"name":"arXiv - CS - Graphics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Fine-grained Metrics for Point Cloud Semantic Segmentation\",\"authors\":\"Zhuheng Lu, Ting Wu, Yuewei Dai, Weiqing Li, Zhiyong Su\",\"doi\":\"arxiv-2407.21289\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Two forms of imbalances are commonly observed in point cloud semantic\\nsegmentation datasets: (1) category imbalances, where certain objects are more\\nprevalent than others; and (2) size imbalances, where certain objects occupy\\nmore points than others. Because of this, the majority of categories and large\\nobjects are favored in the existing evaluation metrics. This paper suggests\\nfine-grained mIoU and mAcc for a more thorough assessment of point cloud\\nsegmentation algorithms in order to address these issues. Richer statistical\\ninformation is provided for models and datasets by these fine-grained metrics,\\nwhich also lessen the bias of current semantic segmentation metrics towards\\nlarge objects. The proposed metrics are used to train and assess various\\nsemantic segmentation algorithms on three distinct indoor and outdoor semantic\\nsegmentation datasets.\",\"PeriodicalId\":501174,\"journal\":{\"name\":\"arXiv - CS - Graphics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Graphics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.21289\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Graphics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.21289","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在点云语义分割数据集中通常会观察到两种形式的不平衡:(1) 类别不平衡,即某些物体比其他物体更普遍;(2) 大小不平衡,即某些物体比其他物体占据更多的点。正因为如此,在现有的评估指标中,大多数类别和大型对象都受到了青睐。本文建议采用精细度的 mIoU 和 mAcc 对点云分割算法进行更全面的评估,以解决这些问题。这些细粒度指标为模型和数据集提供了更丰富的统计信息,同时也减少了当前语义分割指标对大型物体的偏见。所提出的指标被用于在三个不同的室内和室外语义分割数据集上训练和评估各种语义分割算法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Fine-grained Metrics for Point Cloud Semantic Segmentation
Two forms of imbalances are commonly observed in point cloud semantic segmentation datasets: (1) category imbalances, where certain objects are more prevalent than others; and (2) size imbalances, where certain objects occupy more points than others. Because of this, the majority of categories and large objects are favored in the existing evaluation metrics. This paper suggests fine-grained mIoU and mAcc for a more thorough assessment of point cloud segmentation algorithms in order to address these issues. Richer statistical information is provided for models and datasets by these fine-grained metrics, which also lessen the bias of current semantic segmentation metrics towards large objects. The proposed metrics are used to train and assess various semantic segmentation algorithms on three distinct indoor and outdoor semantic segmentation datasets.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信