---
license: mit
datasets:
- nlphuji/flickr30k
language:
- en
---
# Dataset Card for Conditional Latent Coding (CLC)

## Dataset Description

- **Repository:** [GitHub - ydchen0806/CLC](https://github.com/ydchen0806/CLC)
- **Paper:** [Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression (AAAI25 Oral)](https://arxiv.org/pdf/2502.09971)
- **Authors:** Siqi Wu†, Yinda Chen†, Dong Liu, Zhihai He*
- **Contact:** cyd0806@mail.ustc.edu.cn

## Overview

This repository contains datasets and pre-trained models for the **Conditional Latent Coding (CLC)** framework, a state-of-the-art deep image compression method. The implementation is built on [CompressAI](https://github.com/InterDigitalInc/CompressAI) and [TCM](https://github.com/jmliu206/LIC_TCM).


## Dataset Structure

### Core Components
1. **Reference Features** (`flicker_features.pkl`):
   - Precomputed feature dictionary using spatial pyramid pooling and k-means clustering
   - Format: Pickle file containing clustered image features

2. **Training Dataset** (`Flickr2K.hdf5`):
   - Contains 2,650 high-resolution images (256×256 patches)
   - HDF5 structure:
     ```
     /Flickr2K
         ├── image_0001
         ├── image_0002
         └── ...
     ```

3. **Pre-trained Models**:
   - Multiple rate points (0.0025-0.05 bpp):
     - `0.0025checkpoint_best.pth.tar`
     - `0.05checkpoint_best.pth.tar`
   - Compatibility: PyTorch 1.7+ with CUDA support

## 📜 Citation

If you use this model or find it useful, please cite:

```bibtex
@article{wu2025conditional,
  title={Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression},
  author={Wu, Siqi and Chen, Yinda and Liu, Dong and He, Zhihai},
  journal={AAAI Conference on Artificial Intelligence},
  year={2025}
}
```

## 📧 Contact

For questions or collaborations, feel free to reach out:

- **GitHub**: [CLC Repository](https://github.com/ydchen0806/CLC)  
- **Email**: [cyd3933529@gmail.com](mailto:cyd0806@mail.ustc.edu.cn)