---
language:
- en
pipeline_tag: image-classification
tags:
- pytorch
- clip
- generated-image-detection
- image-forensics
---

# 🔍 DoU — Diversity over Uniformity

**Diversity over Uniformity: Rethinking Representation in Generated Image Detection**  
**CVPR 2026**

[📄 Paper](https://openaccess.thecvf.com/content/CVPR2026/papers/He_Diversity_over_Uniformity_Rethinking_Representation_in_Generated_Image_Detection_CVPR_2026_paper.pdf) · [💻 GitHub](https://github.com/Yanmou-Hui/DoU) · [🤗 Weights](https://huggingface.co/Yanmou/DoU/tree/main)

DoU detects AI-generated images by preserving **diverse and complementary forensic cues**, reducing reliance on a few dominant features.


## 🧠 Model Overview

Built on **CLIP ViT-L/14**, DoU combines:

- **Cue Information Bottleneck (CIB):** filters task-irrelevant information from multi-layer visual features.
- **Adaptive Feature Correlation Learning (AFCL):** reduces redundancy among forensic cues during training.
- **Learnable aggregation and prompts:** combine complementary cues for real/generated classification.

| Input | Output |
|:--|:--|
| RGB image, preprocessed to 224 × 224 | **0: Real · 1: Generated** |

The generated-image score is `softmax(logits)[:, 1]`.

## 🚀 Quick Start

### 1. Download and install

```bash
git clone https://huggingface.co/Yanmou/DoU
cd DoU
python -m pip install -r requirements.txt
```

Install a compatible **PyTorch/torchvision** pair for your platform. Model initialization also requires the original OpenAI CLIP backbone, downloaded automatically on first use.

### 2. Run inference

```bash
python infer.py --repo-id Yanmou/DoU --image example.jpg --device cpu --seed 42
```

For GPU inference, use `--device cuda`.

**Using a local checkpoint:**

```bash
python infer.py --ckpt best.pth --image example.jpg --device cpu --seed 42
```

> **Note:** This is a custom PyTorch model; use the provided inference script rather than a Transformers pipeline.

## 🖼️ Preprocessing

The evaluation transform follows the official implementation:

1. Convert to **RGB**.
2. If either dimension is below 224, **tile the image** until both dimensions reach at least 224.
3. **Center-crop to 224 × 224**, convert to a tensor, and apply CLIP normalization.

```python
mean = [0.48145466, 0.4578275, 0.40821073]
std  = [0.26862954, 0.26130258, 0.27577711]
```

**No resizing is applied.** A standard CLIP resize-and-crop processor is therefore not equivalent.

## 📊 Benchmark Evaluation

Organize the evaluation data as follows:

```text
test_root/
├── progan/
│   ├── 0_real/
│   └── 1_fake/
└── stylegan/
    ├── 0_real/
    └── 1_fake/
```

From the `upstream/` directory, run:

```bash
python test.py --ckpt ../best.pth --data-root /path/to/test_root --datasets progan stylegan --device cpu --batch-size 16 --num-workers 0 --output result.xlsx
```

The script reports **ACC, Real ACC, Fake ACC, F1, and AP**, and saves results to Excel.

## ⚙️ Implementation Notes

- **Checkpoint:** a PyTorch dictionary containing the state dictionary under `ckpt["model"]`.
- **Inference:** the variational bottleneck samples features even in `eval()` mode. The inference script sets a seed; outputs may still vary across devices and environments.
- **Source snapshot:** `upstream/` contains official code from commit `230856fabd137e00580d5457b3b1ce7b664bcf99`.
- **Scope:** binary image detection for research. Scores are not calibrated authenticity probabilities, and predictions do not establish image provenance.

## 📜 License

See [`upstream/LICENSE`](upstream/LICENSE) for the source code license and [`WEIGHTS_LICENSE.txt`](WEIGHTS_LICENSE.txt) for the checkpoint terms.

## 📚 Citation

If you find this work useful, please cite:

```bibtex
@inproceedings{he2026diversity,
  title={Diversity over uniformity: Rethinking representation in generated image detection},
  author={He, Qinghui and Zhang, Haifeng and Qin, Qiao and Liu, Bo and Bi, Xiuli and Xiao, Bin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={40407--40417},
  year={2026}
}
```