基于互补熵目标和自适应共识的标签改进的部分域自适应分布对齐

Sandipan Choudhuri, Suli Adeniye, Arunabha Sen
{"title":"基于互补熵目标和自适应共识的标签改进的部分域自适应分布对齐","authors":"Sandipan Choudhuri, Suli Adeniye, Arunabha Sen","doi":"10.47852/bonviewaia2202524","DOIUrl":null,"url":null,"abstract":"In this work, we address a realistic case of unsupervised domain adaptation, where the source label set subsumes that of the target. This relaxation in the requirement of an identical label set assumption, as witnessed in the standard closed-set variant, poses a challenging obstacle of negative transfer that potentially misleads the learning process from the intended target classification objective. To counteract this issue, we propose a novel framework for a partial domain adaptation setup that enforces domain and category-level alignments through optimization of intra- and inter-class distances, uncertainty suppression on classifier predictions, and target supervision with an adaptive consensus-based sample filtering. In this work, we aim to modify the latent space arrangement where samples from identical classes are forced to reside in close proximity while that from distinct classes are well separated in a domain-agnostic fashion. In addition, the proposed model addresses a challenging issue of uncertainty propagation by employing a complement entropy objective that requires the incorrect classes to have uniformly distributed low-prediction probabilities. Target supervision is ensured by employing a robust technique for adaptive pseudo-label generation using a nonparametric classifier. The methodology employs a strategy that permits supervision from target samples with prediction probabilities higher than an adaptive threshold. We conduct experiments involving a range of partial domain adaptation tasks on two benchmark datasets to thoroughly assess the proposed model’s performance against the state-of-the-art methods. In addition, we performed an ablation study to validate the necessity of the incorporated modules and highlight their contribution to the proposed framework. The experimental findings obtained manifest the superior performance of the proposed model when compared to the benchmarks.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"133 5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Distribution Alignment Using Complement Entropy Objective and Adaptive Consensus-Based Label Refinement For Partial Domain Adaptation\",\"authors\":\"Sandipan Choudhuri, Suli Adeniye, Arunabha Sen\",\"doi\":\"10.47852/bonviewaia2202524\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work, we address a realistic case of unsupervised domain adaptation, where the source label set subsumes that of the target. This relaxation in the requirement of an identical label set assumption, as witnessed in the standard closed-set variant, poses a challenging obstacle of negative transfer that potentially misleads the learning process from the intended target classification objective. To counteract this issue, we propose a novel framework for a partial domain adaptation setup that enforces domain and category-level alignments through optimization of intra- and inter-class distances, uncertainty suppression on classifier predictions, and target supervision with an adaptive consensus-based sample filtering. In this work, we aim to modify the latent space arrangement where samples from identical classes are forced to reside in close proximity while that from distinct classes are well separated in a domain-agnostic fashion. In addition, the proposed model addresses a challenging issue of uncertainty propagation by employing a complement entropy objective that requires the incorrect classes to have uniformly distributed low-prediction probabilities. Target supervision is ensured by employing a robust technique for adaptive pseudo-label generation using a nonparametric classifier. The methodology employs a strategy that permits supervision from target samples with prediction probabilities higher than an adaptive threshold. We conduct experiments involving a range of partial domain adaptation tasks on two benchmark datasets to thoroughly assess the proposed model’s performance against the state-of-the-art methods. In addition, we performed an ablation study to validate the necessity of the incorporated modules and highlight their contribution to the proposed framework. The experimental findings obtained manifest the superior performance of the proposed model when compared to the benchmarks.\",\"PeriodicalId\":91205,\"journal\":{\"name\":\"Artificial intelligence and applications (Commerce, Calif.)\",\"volume\":\"133 5 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial intelligence and applications (Commerce, Calif.)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.47852/bonviewaia2202524\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial intelligence and applications (Commerce, Calif.)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.47852/bonviewaia2202524","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

在这项工作中,我们解决了一个无监督域自适应的现实情况,其中源标签集包含目标标签集。正如在标准闭集变体中所看到的那样,这种对相同标签集假设要求的放松带来了负迁移的挑战性障碍,这可能会误导学习过程偏离预期的目标分类目标。为了解决这个问题,我们提出了一个新的部分领域自适应设置框架,该框架通过优化类内和类间距离、分类器预测的不确定性抑制以及基于自适应共识的样本过滤的目标监督来强制领域和类别级别的对齐。在这项工作中,我们的目标是修改潜在空间安排,其中来自相同类别的样本被迫靠近居住,而来自不同类别的样本以领域不可知的方式很好地分离。此外,提出的模型通过采用补熵目标来解决不确定性传播的一个具有挑战性的问题,该目标要求不正确的类具有均匀分布的低预测概率。通过采用非参数分类器自适应伪标签生成鲁棒技术来确保目标监督。该方法采用一种策略,允许来自目标样本的监督,其预测概率高于自适应阈值。我们在两个基准数据集上进行了涉及一系列部分领域自适应任务的实验,以彻底评估所提出的模型与最先进方法的性能。此外,我们进行了消融研究,以验证合并模块的必要性,并强调它们对拟议框架的贡献。实验结果表明,该模型的性能优于基准模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Distribution Alignment Using Complement Entropy Objective and Adaptive Consensus-Based Label Refinement For Partial Domain Adaptation
In this work, we address a realistic case of unsupervised domain adaptation, where the source label set subsumes that of the target. This relaxation in the requirement of an identical label set assumption, as witnessed in the standard closed-set variant, poses a challenging obstacle of negative transfer that potentially misleads the learning process from the intended target classification objective. To counteract this issue, we propose a novel framework for a partial domain adaptation setup that enforces domain and category-level alignments through optimization of intra- and inter-class distances, uncertainty suppression on classifier predictions, and target supervision with an adaptive consensus-based sample filtering. In this work, we aim to modify the latent space arrangement where samples from identical classes are forced to reside in close proximity while that from distinct classes are well separated in a domain-agnostic fashion. In addition, the proposed model addresses a challenging issue of uncertainty propagation by employing a complement entropy objective that requires the incorrect classes to have uniformly distributed low-prediction probabilities. Target supervision is ensured by employing a robust technique for adaptive pseudo-label generation using a nonparametric classifier. The methodology employs a strategy that permits supervision from target samples with prediction probabilities higher than an adaptive threshold. We conduct experiments involving a range of partial domain adaptation tasks on two benchmark datasets to thoroughly assess the proposed model’s performance against the state-of-the-art methods. In addition, we performed an ablation study to validate the necessity of the incorporated modules and highlight their contribution to the proposed framework. The experimental findings obtained manifest the superior performance of the proposed model when compared to the benchmarks.
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
期刊最新文献
Methodology of Measurement Intellectualization based on Regularized Bayesian Approach in Uncertain Conditions Stochastic Dual Coordinate Ascent for Learning Sign Constrained Linear Predictors Data Smoothing Filling Method based on ScRNA-Seq Data Zero-Value Identification Batch-Stochastic Sub-Gradient Method for Solving Non-Smooth Convex Loss Function Problems Teaching Reading Skills More Effectively
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1