Polish ForensicConcept model card

README.md

@@ -4,20 +4,70 @@ library_name: pytorch
 pipeline_tag: image-classification
 tags:
   - aigc-detection
+  - ai-generated-image-detection
   - image-forensics
   - pytorch
+  - dinov3
+  - clip
   - icml-2026
 ---
 
-# ForensicConcept Weights
+<div align="center">
 
-Official detector checkpoints for **ForensicConcept: Transferable Forensic
-Concepts for AIGI Detection**.
+# 🔍 ForensicConcept
 
-- Code: https://github.com/EthanAdamm/FORENSICCONCEPT
-- Paper: https://arxiv.org/abs/2606.07034
+### Transferable Forensic Concepts for AIGI Detection
 
-## Files
+Official detector checkpoints for the ICML 2026 paper
+**ForensicConcept: Transferable Forensic Concepts for AIGI Detection**.
+
+[[`Code`](https://github.com/EthanAdamm/FORENSICCONCEPT)]
+[[`Paper`](https://arxiv.org/abs/2606.07034)]
+[[`Models`](https://huggingface.co/ethan225/ForensicConcept/tree/main/weights)]
+[[`BibTeX`](#citation)]
+
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)
+[![PyTorch](https://img.shields.io/badge/PyTorch-2.7%2B-ee4c2c.svg)](https://pytorch.org/)
+[![ICML 2026](https://img.shields.io/badge/ICML-2026-8A2BE2.svg)](https://icml.cc/)
+
+</div>
+
+---
+
+## Model Overview
+
+ForensicConcept converts diffuse detector evidence into explicit, auditable
+forensic concepts and transfers these concepts across detector backbones. The
+framework combines:
+
+- **Adapter-guided discriminative tuning (ADT)** for efficient detector
+  adaptation with LoRA;
+- **Unsupervised concept induction (UCI)** for discovering a compact forensic
+  concept codebook from decision-critical image patches;
+- **Concept-aligned projection (CAP)** for concept-space prediction;
+- **Concept-guided codebook injection (CGCI)** for transferring
+  diffusion-derived generation traces to target backbones.
+
+<div align="center">
+  <img src="https://raw.githubusercontent.com/EthanAdamm/FORENSICCONCEPT/main/assets/readme/method_overview.png" alt="ForensicConcept overview" width="95%" />
+</div>
+
+## Performance
+
+Image-level accuracy (%) reported in the paper. Models are trained on Stable
+Diffusion 1.4 images.
+
+| Evaluation benchmark | DINOv3 without concepts | ForensicConcept |
+|---|---:|---:|
+| GenImage, mean over 8 generators | 90.7 | **92.0** |
+| GAN-family, mean over 7 generators | 87.3 | **90.1** |
+| Chameleon | 83.7 | **84.4** |
+| Mean over the three benchmarks | 87.2 | **88.8** |
+
+The transferred codebook also raises CLIP ViT-L/14 mean accuracy on GenImage
+from **83.7** to **88.2** (+4.5 points).
+
+## Available Files
 
 | File | Purpose | Size |
 |---|---|---:|
@@ -25,13 +75,24 @@ Concepts for AIGI Detection**.
 | `weights/detectors/dinov3_vitl16_concept_stage2.pth` | DINOv3 ForensicConcept inference | 26.6 MiB |
 | `weights/detectors/clip_vitl14_lora_stage1.pth` | CLIP LoRA initialization | 4.6 MiB |
 | `weights/detectors/clip_vitl14_codebook_stage2.pth` | CLIP CGCI inference | 20.5 MiB |
-| `weights/concepts/dinov3_concept_matrix.npy` | DINOv3 concept initialization (`200 x 1024`, float32) | 0.8 MiB |
+| `weights/concepts/dinov3_concept_matrix.npy` | DINOv3 concepts (`200 x 1024`, float32) | 0.8 MiB |
 
-The four detector checkpoints total 76.0 MiB. Stage-1 checkpoints are included
-for reproducing stage-2 training. For inference, use the corresponding stage-2
-checkpoint. DINOv3 inference also requires the released concept matrix.
+The four detector checkpoints total **76.0 MiB**. Stage-1 checkpoints are
+provided for reproducing stage-2 training. For inference, use the
+corresponding stage-2 checkpoint. DINOv3 inference also requires the released
+concept matrix.
 
-## Download
+## Quick Start
+
+### 1. Clone the code
+
+```bash
+git clone https://github.com/EthanAdamm/FORENSICCONCEPT.git
+cd FORENSICCONCEPT
+python -m pip install -r requirements.txt
+```
+
+### 2. Download the released weights
 
 Run this command from the root of the cloned code repository:
 
@@ -41,11 +102,57 @@ hf download ethan225/ForensicConcept \
   --local-dir .
 ```
 
+### 3. Add the external backbones
+
 The pretrained DINOv3 ViT-L/16 and CLIP ViT-L/14 backbones are not included.
-Download them from their official upstream projects and follow the directory
-layout documented in the code repository.
+Download them from their official upstream projects and use this layout:
+
+```text
+weights/
+|-- backbones/
+|   |-- ViT-L-14.pt
+|   `-- dinov3-vitl16/
+|       `-- model.safetensors
+|-- concepts/
+|   `-- dinov3_concept_matrix.npy
+`-- detectors/
+    |-- dinov3_vitl16_lora_stage1.pth
+    |-- dinov3_vitl16_concept_stage2.pth
+    |-- clip_vitl14_lora_stage1.pth
+    `-- clip_vitl14_codebook_stage2.pth
+```
 
-## SHA-256
+### 4. Evaluate
+
+```bash
+# DINOv3 ForensicConcept
+python test_with_config.py \
+  --config configs/dinov3_concept.yaml \
+  --checkpoint_path weights/detectors/dinov3_vitl16_concept_stage2.pth
+
+# CLIP with concept-guided codebook injection
+python test_with_config.py \
+  --config configs/clip_codebook.yaml \
+  --checkpoint_path weights/detectors/clip_vitl14_codebook_stage2.pth
+```
+
+Dataset paths are placeholders in the public configurations. Update
+`data.*` and `testing.groups` before evaluation. See the
+[`GitHub README`](https://github.com/EthanAdamm/FORENSICCONCEPT#dataset-preparation)
+for complete installation, dataset, training, and evaluation instructions.
+
+## Checkpoint Notes
+
+- DINOv3 stage 2 contains the classifier, concept mapping/head, and all LoRA
+  tensors. The external concept matrix initializes the model structure before
+  loading the checkpoint.
+- CLIP stage 2 contains visual LoRA, the main classifier, and the complete
+  codebook head.
+- External backbone weights remain subject to their respective upstream
+  licenses and terms.
+
+<details>
+<summary><strong>SHA-256 checksums</strong></summary>
 
 ```text
 3bc8e833d75c9ccbb214c28238c791681294ae8b0c50e48cc3e64b9e5ac5ca1f  weights/detectors/dinov3_vitl16_lora_stage1.pth
@@ -55,6 +162,19 @@ a81ebec9281aca3db4b0d88254d25424f37d5d498ae2c405eb6a5be4748dc498  weights/detect
 9e6ce224d223dab804648bb46a9cc405bfef4cfcb13dc9cc21ad7fd94935959c  weights/concepts/dinov3_concept_matrix.npy
 ```
 
+</details>
+
+## Citation
+
+```bibtex
+@inproceedings{zhou2026forensicconcept,
+  title     = {{ForensicConcept}: Transferable Forensic Concepts for {AIGI} Detection},
+  author    = {Zhou, Menyanshu and Zhou, Ziyin and Sun, Ke and Luo, Yunpeng and Ji, Jiayi and Sun, Xiaoshuai and Ji, Rongrong},
+  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
+  year      = {2026}
+}
+```
+
 ## License
 
 The ForensicConcept detector checkpoints are released under the