融合环境标签平滑与核范数差异的领域自适应  

Domain adaptation integrating environment label smoothing and nuclear norm discrepancy

作　　者：丁美荣 卓金鑫 陆玉武 刘庆龙 郎济聪 DING Meirong;ZHUO Jinxin;LU Yuwu;LIU Qinglong;LANG Jicong(School of Software,South China Normal University,Foshan Guangdong 528225,China)

机构地区：[1]华南师范大学软件学院,广东佛山528225

出　　处：《计算机应用》2025年第4期1130-1138,共9页journal of Computer Applications

基　　金：国家自然科学基金资助项目(62176162);广东省自然科学基金资助项目(2022A1515140099,2023A1515012875)。

摘　　要：现有的领域自适应方法过于关注源域的细粒度特征学习,从而削弱了相关方法有效推广到目标域的能力,导致这些方法容易在特定的环境中过度拟合,且缺乏对复杂环境的鲁棒性。为了解决上述问题,提出一个融合环境标签平滑与核范数差异(ELSND)的领域自适应模型。所提模型通过环境标签平滑模块,减小真实标签的概率,增大非真实标签的概率,进而增强模型对不同场景的适应性。同时,运用核范数差异模块度量源域与目标域的分布差异,从而提高决策边界处样本的分类确定性。在Office-31、Office-Home和MiniDomainNet这3个领域的自适应基准数据集上进行大量实验。结果表明,与先进的基线模型DomainAdaptor-Aug(DomainAdaptor with generalized entropy minimization-Augmentation)在MiniDomainNet数据集上相比,ELSND模型在图像分类领域自适应任务上的精确度提升了1.23个百分点。因此,所提模型在图像分类时具有更高的精确度和泛化性。The existing domain adaptation methods overly focus on fine-grained feature learning in the source domain,hindering their ability to extend to the target domain effectively,making them prone to overfitting in specific environments,and lacking robustness to complex environments.To address the above mentioned issues,a domain adaptation model that integrates Environment Label Smoothing and Nuclear norm Discrepancy(ELSND)was proposed.In the proposed model,through the environment label smoothing module,the probability of true labels was reduced and the probability of non-true labels was increased to enhance the model adaptability to different scenarios.At the same time,the nuclear norm discrepancy module was employed to measure distribution difference between the source and target domains,thereby improving the classification certainty at decision boundaries.Large number of experiments were conducted on adaptive benchmark datasets of three domains including Office-31,Office-Home and MiniDomainNet.Compared with the state-of-theart baseline model DomainAdaptor-Aug(DomainAdaptor with generalized entropy minimization-Augmentation)on MiniDomainNet dataset,ELSND model achieves a 1.23 percentage points increase in accuracy of image classification domain adaptation tasks.Therefore,the proposed model has a higher precision and generalization in image classification.

关 键 词：领域自适应 迁移学习 图像分类 核范数 对抗学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]