基于梯度的类加权在密集预测视觉任务中的无监督域自适应

IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Roberto Alcover-Couso , Marcos Escudero-Viñolo, Juan C. SanMiguel, Jesus Bescos
{"title":"基于梯度的类加权在密集预测视觉任务中的无监督域自适应","authors":"Roberto Alcover-Couso ,&nbsp;Marcos Escudero-Viñolo,&nbsp;Juan C. SanMiguel,&nbsp;Jesus Bescos","doi":"10.1016/j.patcog.2025.111633","DOIUrl":null,"url":null,"abstract":"<div><div>In unsupervised domain adaptation (UDA), where models are trained on source data (e.g., synthetic) and adapted to target data (e.g., real-world) without target annotations, addressing the challenge of significant class imbalance remains an open issue. Despite progress in bridging the domain gap, existing methods often experience performance degradation when confronted with highly imbalanced dense prediction visual tasks like semantic segmentation. This discrepancy becomes especially pronounced due to the lack of equivalent priors between the source and target domains, turning class imbalanced techniques used for other areas (e.g., image classification) ineffective in UDA scenarios. This paper proposes a class-imbalance mitigation strategy that incorporates class-weights into the UDA learning losses, with the novelty of estimating these weights dynamically through the gradients of the per-class losses, defining a Gradient-based class weighting (GBW) approach. The proposed GBW naturally increases the contribution of classes whose learning is hindered by highly-represented classes, and has the advantage of automatically adapting to training outcomes, avoiding explicit curricular learning patterns common in loss-weighing strategies. Extensive experimentation validates the effectiveness of GBW across architectures (Convolutional and Transformer), UDA strategies (adversarial, self-training and entropy minimization), tasks (semantic and panoptic segmentation), and datasets. Analysis shows that GBW consistently increases the recall of under-represented classes.</div></div>","PeriodicalId":49713,"journal":{"name":"Pattern Recognition","volume":"166 ","pages":"Article 111633"},"PeriodicalIF":7.5000,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Gradient-based class weighting for unsupervised domain adaptation in dense prediction visual tasks\",\"authors\":\"Roberto Alcover-Couso ,&nbsp;Marcos Escudero-Viñolo,&nbsp;Juan C. SanMiguel,&nbsp;Jesus Bescos\",\"doi\":\"10.1016/j.patcog.2025.111633\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>In unsupervised domain adaptation (UDA), where models are trained on source data (e.g., synthetic) and adapted to target data (e.g., real-world) without target annotations, addressing the challenge of significant class imbalance remains an open issue. Despite progress in bridging the domain gap, existing methods often experience performance degradation when confronted with highly imbalanced dense prediction visual tasks like semantic segmentation. This discrepancy becomes especially pronounced due to the lack of equivalent priors between the source and target domains, turning class imbalanced techniques used for other areas (e.g., image classification) ineffective in UDA scenarios. This paper proposes a class-imbalance mitigation strategy that incorporates class-weights into the UDA learning losses, with the novelty of estimating these weights dynamically through the gradients of the per-class losses, defining a Gradient-based class weighting (GBW) approach. The proposed GBW naturally increases the contribution of classes whose learning is hindered by highly-represented classes, and has the advantage of automatically adapting to training outcomes, avoiding explicit curricular learning patterns common in loss-weighing strategies. Extensive experimentation validates the effectiveness of GBW across architectures (Convolutional and Transformer), UDA strategies (adversarial, self-training and entropy minimization), tasks (semantic and panoptic segmentation), and datasets. Analysis shows that GBW consistently increases the recall of under-represented classes.</div></div>\",\"PeriodicalId\":49713,\"journal\":{\"name\":\"Pattern Recognition\",\"volume\":\"166 \",\"pages\":\"Article 111633\"},\"PeriodicalIF\":7.5000,\"publicationDate\":\"2025-04-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Pattern Recognition\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0031320325002936\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pattern Recognition","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0031320325002936","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

在无监督域自适应(UDA)中,模型在源数据(例如,合成)上进行训练,并在没有目标注释的情况下适应目标数据(例如,现实世界),解决重大类不平衡的挑战仍然是一个悬而未决的问题。尽管在弥合领域差距方面取得了进展,但当面对语义分割等高度不平衡的密集预测视觉任务时,现有方法往往会出现性能下降。由于源域和目标域之间缺乏等效的先验,这种差异变得特别明显,使得用于其他领域(例如,图像分类)的类不平衡技术在UDA场景中无效。本文提出了一种将类权重纳入UDA学习损失的类失衡缓解策略,其新颖之处是通过每类损失的梯度动态估计这些权重,定义了一种基于梯度的类加权(GBW)方法。所提出的GBW自然地增加了那些学习受到高代表性班级阻碍的班级的贡献,并且具有自动适应训练结果的优势,避免了减肥策略中常见的明确的课程学习模式。大量的实验验证了跨架构(卷积和变压器)、UDA策略(对抗、自我训练和熵最小化)、任务(语义和全景分割)和数据集的GBW的有效性。分析表明,GBW持续增加了代表性不足班级的召回率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Gradient-based class weighting for unsupervised domain adaptation in dense prediction visual tasks

Gradient-based class weighting for unsupervised domain adaptation in dense prediction visual tasks
In unsupervised domain adaptation (UDA), where models are trained on source data (e.g., synthetic) and adapted to target data (e.g., real-world) without target annotations, addressing the challenge of significant class imbalance remains an open issue. Despite progress in bridging the domain gap, existing methods often experience performance degradation when confronted with highly imbalanced dense prediction visual tasks like semantic segmentation. This discrepancy becomes especially pronounced due to the lack of equivalent priors between the source and target domains, turning class imbalanced techniques used for other areas (e.g., image classification) ineffective in UDA scenarios. This paper proposes a class-imbalance mitigation strategy that incorporates class-weights into the UDA learning losses, with the novelty of estimating these weights dynamically through the gradients of the per-class losses, defining a Gradient-based class weighting (GBW) approach. The proposed GBW naturally increases the contribution of classes whose learning is hindered by highly-represented classes, and has the advantage of automatically adapting to training outcomes, avoiding explicit curricular learning patterns common in loss-weighing strategies. Extensive experimentation validates the effectiveness of GBW across architectures (Convolutional and Transformer), UDA strategies (adversarial, self-training and entropy minimization), tasks (semantic and panoptic segmentation), and datasets. Analysis shows that GBW consistently increases the recall of under-represented classes.
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
Pattern Recognition
Pattern Recognition 工程技术-工程:电子与电气
CiteScore
14.40
自引率
16.20%
发文量
683
审稿时长
5.6 months
期刊介绍: The field of Pattern Recognition is both mature and rapidly evolving, playing a crucial role in various related fields such as computer vision, image processing, text analysis, and neural networks. It closely intersects with machine learning and is being applied in emerging areas like biometrics, bioinformatics, multimedia data analysis, and data science. The journal Pattern Recognition, established half a century ago during the early days of computer science, has since grown significantly in scope and influence.
×
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