HNH

---

This repository is for "High-order nonlocal Hashing for unsupervised cross-modal retrieval"

---

Usage

Requirements

• python == 3.11.5
• pytorch == 2.1.0
• torchvision
• CV2
• PIL
• h5py

Datasets

For datasets, we follow Deep Cross-Modal Hashing's Github (Jiang, CVPR 2017). You can download these datasets from:

• Wikipedia articles, Link
• MIRFLICKR25K, [OneDrive], [Baidu Pan, password: 8dub]
• NUS-WIDE (top-10 concept), [OneDrive], [Baidu Pan, password: ml4y]

Process

The following experiment results are the average values, if you demand for better results, please run the experiment a few more times (2~5).

• Clone this repo: git clone https://github.com/youonly-once/HNH.git.
• Change the 'dataPath' in default_config.yml to where you place the datasets.
• An example to train a model:

python main.py

• Modify the parameter eval = True in default_config.yml for validation.
• Ablation studies (optional): if you want to evaluate other components of our HNH, please refer to our paper and default_config.yml.

---

All rights are reserved by the authors.

---