反思半监督地标检测的自我训练:无选择方法

Haibo Jin;Haoxuan Che;Hao Chen
{"title":"反思半监督地标检测的自我训练:无选择方法","authors":"Haibo Jin;Haoxuan Che;Hao Chen","doi":"10.1109/TIP.2024.3451937","DOIUrl":null,"url":null,"abstract":"Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection faces three problems: 1) The selected confident pseudo-labels often contain data bias, which may hurt model performance; 2) It is not easy to decide a proper threshold for sample selection as the localization task can be sensitive to noisy pseudo-labels; 3) coordinate regression does not output confidence, making selection-based self-training infeasible. To address the above issues, we propose Self-Training for Landmark Detection (STLD), a method that does not require explicit pseudo-label selection. Instead, STLD constructs a task curriculum to deal with confirmation bias, which progressively transitions from more confident to less confident tasks over the rounds of self-training. Pseudo pretraining and shrink regression are two essential components for such a curriculum, where the former is the first task of the curriculum for providing a better model initialization and the latter is further added in the later rounds to directly leverage the pseudo-labels in a coarse-to-fine manner. Experiments on three facial and one medical landmark detection benchmark show that STLD outperforms the existing methods consistently in both semi- and omni-supervised settings. The code is available at \n<uri>https://github.com/jhb86253817/STLD</uri>\n.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Rethinking Self-Training for Semi-Supervised Landmark Detection: A Selection-Free Approach\",\"authors\":\"Haibo Jin;Haoxuan Che;Hao Chen\",\"doi\":\"10.1109/TIP.2024.3451937\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection faces three problems: 1) The selected confident pseudo-labels often contain data bias, which may hurt model performance; 2) It is not easy to decide a proper threshold for sample selection as the localization task can be sensitive to noisy pseudo-labels; 3) coordinate regression does not output confidence, making selection-based self-training infeasible. To address the above issues, we propose Self-Training for Landmark Detection (STLD), a method that does not require explicit pseudo-label selection. Instead, STLD constructs a task curriculum to deal with confirmation bias, which progressively transitions from more confident to less confident tasks over the rounds of self-training. Pseudo pretraining and shrink regression are two essential components for such a curriculum, where the former is the first task of the curriculum for providing a better model initialization and the latter is further added in the later rounds to directly leverage the pseudo-labels in a coarse-to-fine manner. Experiments on three facial and one medical landmark detection benchmark show that STLD outperforms the existing methods consistently in both semi- and omni-supervised settings. The code is available at \\n<uri>https://github.com/jhb86253817/STLD</uri>\\n.\",\"PeriodicalId\":94032,\"journal\":{\"name\":\"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10667011/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10667011/","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

自我训练是一种简单而有效的半监督学习方法,其中伪标签选择在处理确认偏差方面发挥着重要作用。尽管这种方法很受欢迎,但将自我训练应用于地标检测却面临三个问题:1)选择的置信伪标签往往包含数据偏差,这可能会损害模型性能;2)由于定位任务可能对噪声伪标签很敏感,因此决定一个合适的样本选择阈值并不容易;3)坐标回归不输出置信度,这使得基于选择的自我训练变得不可行。为了解决上述问题,我们提出了地标检测自我训练(STLD)方法,这种方法不需要明确的伪标签选择。取而代之的是,STLD 构建了一个处理确认偏差的任务课程,在一轮又一轮的自我训练中,从信心较高的任务逐步过渡到信心较低的任务。伪预训练和收缩回归是这种课程的两个基本组成部分,前者是课程的第一个任务,用于提供更好的模型初始化,后者则在后几轮任务中进一步添加,以从粗到细的方式直接利用伪标签。在三个面部检测基准和一个医疗地标检测基准上的实验表明,STLD 在半监督和全监督环境下的表现始终优于现有方法。代码见 https://github.com/jhb86253817/STLD。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Rethinking Self-Training for Semi-Supervised Landmark Detection: A Selection-Free Approach
Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection faces three problems: 1) The selected confident pseudo-labels often contain data bias, which may hurt model performance; 2) It is not easy to decide a proper threshold for sample selection as the localization task can be sensitive to noisy pseudo-labels; 3) coordinate regression does not output confidence, making selection-based self-training infeasible. To address the above issues, we propose Self-Training for Landmark Detection (STLD), a method that does not require explicit pseudo-label selection. Instead, STLD constructs a task curriculum to deal with confirmation bias, which progressively transitions from more confident to less confident tasks over the rounds of self-training. Pseudo pretraining and shrink regression are two essential components for such a curriculum, where the former is the first task of the curriculum for providing a better model initialization and the latter is further added in the later rounds to directly leverage the pseudo-labels in a coarse-to-fine manner. Experiments on three facial and one medical landmark detection benchmark show that STLD outperforms the existing methods consistently in both semi- and omni-supervised settings. The code is available at https://github.com/jhb86253817/STLD .
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