计算机科学与探索2025，Vol.19Issue(8)：2123-2134,12.DOI:10.3778/j.issn.1673-9418.2407042
基于特征增强和对比嵌入的零样本图像分类算法
Zero-Shot Image Classification Based on Feature Enhancement and Contrastive Embedding
摘要
Abstract
Zero-shot image classification aims to achieve prediction of unseen classes by utilizing the information of the seen classes during the training.The generative method synthesizes visual features of unseen classes using generative model guided by semantic information and trains a supervised learning model in the visual feature space to complete the prediction.However,the visual feature space lacks sufficient discriminative information,and thus the classification results are not optimal.In order to obtain the features with more discriminative information,this paper proposes to build a con-trastive embedding module based on contrastive learning to project the generated features and real features into the con-trastive embedding space,performing contrastive embedding in terms of the instance-level and class-level respectively and using the contrastive learning to better learn the differences between instances as well as the differences between classes.Eventually,a supervised learning model is trained in the contrastive embedding space to complete the prediction.In addition,in order to fully utilize the data distribution of visual features and to obtain generated features that are closer to the real features and their semantic information,this paper utilizes Vision Transformer for visual feature extraction,and dual prototype constraint strategy is added to the feature generation process,utilizing clustering prototype and class proto-type to help the generative model learn the data distribution better.This strategy constrains the generated features to be close to the clustering prototype of the real feature and the class prototype of the generated features to be close to the clus-tering prototype of the real feature.Experiments are conducted on three common datasets and the results show the effec-tiveness of the proposed algorithm.关键词
零样本图像分类/生成模型/对比学习/聚类原型/类别原型Key words
zero-shot image classification/generative model/contrastive learning/clustering prototype/class prototype分类
信息技术与安全科学引用本文复制引用
刘颖,冯小东,何敬鲁..基于特征增强和对比嵌入的零样本图像分类算法[J].计算机科学与探索,2025,19(8):2123-2134,12.基金项目
国家自然科学基金(62301427).This work was supported by the National Natural Science Foundation of China(62301427). （62301427）
