Cross-Modal Remote Sensing Image-Audio Retrieval with Adaptive Learning for Aligning Correlation

Author: Jinghao Huang

-------------------------------------------------------------------------------------

Welcome 👍Fork and Star👍, then we'll let you know when we update

-------------------------------------------------------------------------------------

ALAL

Network Architecture

---

Environment

Python 3.8.0
Pytorch 1.11.0
torchvision 0.12.0
librosa 0.9.1
numpy 1.21.6
tqdm 4.64.0

---

Dataset

We use the following 4 datasets: Sydney Image-Audio Dataset, UCM Image-Audio Dataset, RSICD Image-Audio Dataset and RSITMD Image-Audio Dataset. Dataset download link 1 or Dataset download link 2

---

Pre-trained model

pre-trained model

---

Train

We train our model on a single 3090Ti GPU card. To train on different datasets, one needs to modify the configuration file in the code and then use the following training command:

python train.py

---

Test

python test.py