郑州大学学报（理学版）2026，Vol.58Issue(2)：25-32,8.DOI:10.13705/j.issn.1671-6841.2024147
融合提示学习与分类确定性最大化的领域自适应
Domain Adaptation Based on Prompt Learning and Classification Certainty Maximization
摘要
Abstract
Domain adaptation faced the issue of complex and variable real-world scenarios,and existing methods mostly focused on optimizing classification consistency while neglecting classification certainty.To address these issues,a network model combining constrastive language-image pre-training(CLIP)with classification certainty maximization was proposed.CLIP,as a multimodal pre-trained model,was pre-trained on a large scale of image-text pairs and possessed strong cross-domain generalization capabili-ties.By leveraging prompt learning and contrastive learning,the knowledge of the CLIP model was ac-quired,enabling the model to adapt more complex real-world scenarios.Through the method of classifica-tion certainty maximization,a dual-classifier was employed to assess classification consistency and reduce confusion during the model's inference process.Experiments were conducted on three domain adaptation benchmark datasets:Office-31,Office-Home,and MiniDomainNet.The experimental results indicated that compared with existing advanced methods,the proposed model showed improvements in image classi-fication accuracy across all three datasets.关键词
迁移学习/图像分类/CLIP模型/提示学习/领域自适应/分类确定性Key words
transfer learning/image classification/CLIP model/prompt learning/domain adaptation/classification certainty分类
信息技术与安全科学引用本文复制引用
丁美荣,卓金鑫,刘庆龙,郎济聪..融合提示学习与分类确定性最大化的领域自适应[J].郑州大学学报（理学版）,2026,58(2):25-32,8.基金项目
国家自然科学基金面上项目(62176162) （62176162）
广东省自然科学基金项目(2022A1515140099,2023A1515012875) （2022A1515140099,2023A1515012875）
