计算机与现代化Issue(2)：19-27,9.DOI:10.3969/j.issn.1006-2475.2025.02.003
基于语义拓展和嵌入的零样本学习
Zero-shot Learning Based on Semantic Extension and Embedding
摘要
Abstract
In zero-shot image classification,semantic embedding technology(i.e.,using semantic attributes to describe class la-bels)provides the means to generate visual features for unknown objects by transferring knowledge from known objects.Current research often utilizes class semantic attributes as auxiliary information for describing class visual features.However,class se-mantic attributes are typically obtained through external paradigms such as manual annotation,resulting in weak consistency with visual features.Moreover,a single class semantic attribute is insufficient to capture the diversity of visual features.To en-hance the diversity of class semantic attributes and their capacity to describe visual features,this paper introduces a Semantic Ex-tension and Embedding for Zero-Shot Learning(SeeZSL)based on semantic extension and embedding.SeeZSL expands seman-tic information by constructing a latent semantic space for each class,enabling the generation of visual features for unknown classes using this semantic space.Additionally,to address the issues of weak consistency and the lack of discriminative ability between the original feature space and class semantic attributes,a semantic extension-based generation model is integrated with an contrastive-embedding model.The effectiveness of the proposed SeeZSL method was experimentally validated on four bench-mark datasets.关键词
零样本学习/语义拓展/视觉-语义映射/对比学习Key words
zero-shot learning/semantic expansion/visual-semantic mapping/contrastive learning分类
计算机与自动化引用本文复制引用
郭晨光,茅健,汪云云..基于语义拓展和嵌入的零样本学习[J].计算机与现代化,2025,(2):19-27,9.基金项目
国家自然科学基金资助项目(61876091) （61876091）
