华南理工大学学报（自然科学版）2025，Vol.53Issue(3)：50-56,7.DOI:10.12141/j.issn.1000-565X.240159
基于文本-视觉和信息熵最小化的对比学习模型
Contrastive Learning Model Based on Text-Visual and Information Entropy Minimization
摘要
Abstract
Current unsupervised contrastive learning methods mainly rely on pure textual information to construct sentence embeddings,which presents limitations in comprehensively understanding the deeper meanings conveyed by sentences.Meanwhile,traditional contrastive learning methods focus excessively on maximizing the mutual infor-mation between positive instances of text,overlooking the potential noise interference within sentence embeddings.To effectively retain useful information in the text while eliminating noise interference in the embeddings,the paper proposed a contrastive learning model based on text-vision and information entropy minimization.Firstly,the text and the corresponding visual information are deeply fused under the framework of contrastive learning,and jointly mapped to a unified grounding space,ensuring their representations remain consistent within this space.This approach overcomes the limitations of relying solely on pure textual information for sentence embedding learning,making the contrastive learning process more comprehensive and precise.Secondly,following the principle of informa-tion minimization,the model reconstructs positive text instances based on information entropy minimization while maximizing mutual information between positive text instances.Experimental results on the standard semantic tex-tual similarity(STS)task demonstrate that the proposed model achieves significant improvements in the Spearman correlation coefficient evaluation metric,showcasing a notable advantage over existing state-of-the-art methods.This also confirms the effectiveness of the proposed model.关键词
无监督对比学习/互信息/文本-视觉/信息熵最小化/语义文本相似度Key words
unsupervised contrastive learning/mutual information/text-visual/information entropy minimization/semantic text similarity分类
信息技术与安全科学引用本文复制引用
蔡晓东,董丽芳,黄业洋,周丽..基于文本-视觉和信息熵最小化的对比学习模型[J].华南理工大学学报（自然科学版）,2025,53(3):50-56,7.基金项目
广西创新驱动发展专项(AA20302001) Supported by the Guangxi Innovation-Driven Development Project(AA20302001) （AA20302001）
