广东工业大学学报2025，Vol.42Issue(3)：12-26,15.DOI:10.12052/gdutxb.230188
置信样本选择与差异性特征增强的域适应
Confidence Sample Selection and Specific Feature Enhancement for Domain Adaptation
摘要
Abstract
For domain shifts,domain adaptation(DA)promotes label propagation by reducing distributional differences.In recent work,DA only enhances the discriminability of linear data by linear discriminant analysis,which ignores real-world nonlinear data.Meanwhile,these methods fail to consider the negative impact of the target low-confidence samples on the training process.Therefore,confidence sample selection and specific feature enhancement for domain adaptation(CSS-SFE)is proposed.Firstly,the framework selects target high-confidence samples through the min-max principle to reduce the impact of incorrect pseudo-label during training;Secondly,the class scatter matrix and neighbor scatter matrix are balanced to enhance the features of linear and nonlinear datasets so that the discriminability of the samples is improved;Thirdly,the framework maintains source and target specific features by learning different projection matrices,which prevents the discriminability of the samples decreasing;Fourthly,the marginal and conditional distribution alignment is further applied to reduce the domain distribution discrepancy;Finally,extensive experiments on several benchmark datasets demonstrate the superiority of CSS-SFE over state-of-the-art methods.关键词
高置信样本选择/差异性特征增强/域适应/标签传播Key words
confidence sample selection/specific feature enhancement/domain adaptation/label propagation分类
计算机与自动化引用本文复制引用
滕少华,吴泽锋,滕璐瑶,张巍,曾莹..置信样本选择与差异性特征增强的域适应[J].广东工业大学学报,2025,42(3):12-26,15.基金项目
国家自然科学基金资助项目(61972102) （61972102）
广州市科技计划项目(2023A04J1729) （2023A04J1729）
