ADCD-Net

ADCD-Net addresses the challenging problem of document image forgery localization by leveraging adaptive DCT features alongside hierarchical content disentanglement to robustly detect tampered regions even under compression distortions.

---

📊 ForensicHub Benchmark (Doc Protocol)

Evaluation follows the Doc Protocol: train on the DocTamper training set, evaluate on seven test sets. DocTamper FCD/SCD/Test sets are compressed once using the official DocTamper pickle QFs. Authentic images are skipped.

For more details, see ForensicHub — Doc Protocol.

---

⚙️ Environment Setup

Dependency	Version
Python	3.10.13
PyTorch	2.3.0+cu121
albumentations	2.0.8

---

📂 Data Preparation

1. Download DocTamper Data

Download the DocTamper dataset (Training, Testing, FCD, SCD) from: 👉 DocTamper GitHub

qt_table.pk and pks (JPEG record pickle files) are available in the DocTamper repository.

2. Download ADCD-Net Checkpoints & OCR Masks

Download from Google Drive: 👉 ADCD-Net Data (Google Drive)

The archive contains:

ADCDNet.pth          # ADCD-Net model checkpoint
docres.pkl           # DocRes backbone checkpoint
DocTamperOCR/        # Pre-generated OCR mask directory
├── TrainingSet/     # Training set OCR masks
├── TestingSet/      # Testing set OCR masks
├── FCD/             # FCD dataset OCR masks
└── SCD/             # SCD dataset OCR masks

3. Download Doc Protocol Cross-Domain Test Sets

Download the 4 cross-domain test sets (T-SROIE, OSTF, TPIC-13, RTM) from: 👉 Doc Protocol Data (Google Drive) — cutted_datasets_fakes.zip

---

🔤 Get OCR Masks

OCR character segmentation masks are generated using seg_char.py, which requires PaddleOCR.

Install PaddlePaddle and PaddleOCR by following the official guide: 👉 PaddleOCR Installation

Then run:

python seg_char.py

---

🚀 Training

ADCD-Net is trained on 4 × NVIDIA GeForce RTX 4090 (24 GB) with:

• 100k training steps
• Batch size: 40 (10 per GPU × 4 GPUs with gradient accumulation)
• Training time: ~27 hours

Steps:

1. Configure paths in cfg.py:

mode = 'train'
root = 'path/to/DocTamper'
docres_ckpt_path = 'path/to/docres.pkl'

2. Launch training:

python main.py

---

📈 Evaluation

Reproduce the ForensicHub Doc Protocol results with the following steps:

1. Generate OCR masks for the 4 cross-domain sets using seg_char.py.
2. Generate path pickle files for the 4 sets using build_path_pkl.py.
3. Configure cfg.py for evaluation:

mode = 'val'
all_ds_name = ['TestingSet', 'FCD', 'SCD', 'T-SROIE_test', 'Tampered-IC13_test', 'RealTextManipulation_test', 'OSTF_test']
pkl_dir = 'path/to/path_pkl'

4. Run evaluation:

python main.py

---

📝 Citation

If you find this work useful in your research, please consider citing:

@inproceedings{wong2025adcd,
  title={ADCD-Net: Robust Document Image Forgery Localization via Adaptive DCT Feature and Hierarchical Content Disentanglement},
  author={Wong, Kahim and Zhou, Jicheng and Wu, Haiwei and Si, Yain-Whar and Zhou, Jiantao},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2025}
}