通信学报2025，Vol.46Issue(5)：103-114,12.DOI:10.11959/j.issn.1000-436x.2025076
多模态信息交互的零样本分类及其在火星探测场景的应用
Zero-shot classification with multi-model information interaction and its application in Mars exploration scenarios
摘要
Abstract
To address the issue that traditional Mars image classification methods based on images do not perform well in the face of the complex and unknown environment of Mars and the frequent occurrence of unseen categories,a zero-shot classification algorithm of multi-modal information interaction was studied and the migration and optimization of the al-gorithm to the field of deep space exploration was explored.The research content was mainly divided into two aspects:dataset construction and algorithm research.In terms of dataset construction,the zero-shot classification dataset for Mars exploration was integrated and reconstructed.For algorithm research,a zero-shot scene classification algorithm based on multi-modal feature interaction was proposed.Then combined with knowledge distillation,the model was compressed and optimized,which greatly reduced the number of parameters and complexity of the model while ensuring the perfor-mance of zero-shot classification.To verify the effectiveness of the algorithm,a large number of comparative experi-ments and visualization analysis are carried out,and the results prove the feasibility and effectiveness of the proposed algorithm.关键词
火星图像分类/多模态信息/零样本分类/知识蒸馏Key words
Mars image classification/multi-modal information/zero-shot classification/knowledge distillation分类
计算机与自动化引用本文复制引用
檀晓萌,席博博,薛长斌,李云松..多模态信息交互的零样本分类及其在火星探测场景的应用[J].通信学报,2025,46(5):103-114,12.基金项目
国家自然科学基金资助项目(No.62401434)Foundation Item:The National Natural Science Foundation of China(No.62401434) （No.62401434）
