The official implementation for the paper "Towards Discriminative and Consistent Cross-Modal Alignment for Remote Sensing Image-Text Retrieval"
clip_benchmark==1.6.1
matplotlib==3.7.5
numpy==1.24.1
open_clip_torch==2.24.0
pandas==2.0.3
Pillow==12.0.0
PyYAML==6.0.3
seaborn==0.13.2
torch==2.1.1+cu118
torchvision==0.16.1+cu118
tqdm==4.66.2
wandb==0.12.21
Model training is performed using the scripts/train.sh script, while model testing is conducted using the scripts/test.sh script.
This project is built upon the following open-source repositories. We sincerely thank the authors for their contributions: