aimer_whut 524961fc03 | 1 month ago | |
---|---|---|
layers | 1 month ago | |
option | 1 month ago | |
README.md | 1 month ago | |
Self-Supervision_Interactive_Alignment_for_Remote_Sensing_ImageAudio_Retrieval.pdf | 1 month ago | |
data.py | 1 month ago | |
engine.py | 1 month ago | |
test.py | 1 month ago | |
train.py | 1 month ago | |
utils.py | 1 month ago |
This is the mindspore official repository for SSIA
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10091166
Data set source:
https://github.com/ninghailong/Cross-Modal-Remote-Sensing-Image-Sound-Retrieval
data
├── rsicd_images
├── 00001.jpg
├── 00002.jpg
├── 00003.jpg
├── ...
└── viaduct_9.jpg
├── rsicd_mat
├── test_audios.mat
└── train_audios.mat
└── rsicd_precomp
├── test_auds.txt
├── test_caps.txt
├── test_filename.txt
├── train_auds.txt
├── train_auds_verify.txt
├── train_caps.txt
├── train_filename.txt
├── train_filename_verify.txt
├── val_auds_verify.txt
└── val_filename_verify.txt
跨模态遥感图像-音频(RSIA)检索使用音频或遥感图像作为查询检索相关内容。考虑到标记样本的高成本,SSIA利用未标记样本学习显著信息、跨模态对齐及RSI与音频间的相似性。通过RSI与音频信息的相似性作为监督信息,设计了交互式对齐模块和音频引导的图像去冗余模块,提高检索效率和精确度。在四个主要RSIA数据集上的实验证明,SSIA的性能超越了其他方法。本项目出自:武汉理工大学陈亚雄老师团队
Python
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》