Research map / Image generation / Autoregressive and latent generation
CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection
Zexi Jia, Zhiqiang Yuan, Xiaoyue Duan, Jinchao Zhang, Jie Zhou, Anil K. Jain
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the color branch (Noise-Quantization Probe difference map) to the image branch (ablation) | CoDA image branch · FakeForm 62 domains | accuracy (%): 66.8 -> 77.7 | Improved |
| add the image branch to the color branch (ablation) | CoDA color branch · FakeForm 62 domains | accuracy (%): 58.4 -> 77.7 | Improved |
| add the color branch (ablation) | CoDA image branch · ForenSynths (GAN) | accuracy (%): 95.5 -> 98.7 | Improved |
| add the color branch (ablation) | CoDA image branch · GenImage | accuracy (%): 95.1 -> 95.9 | Improved |
| add the color branch (ablation) | CoDA image branch · FakeForm Games | accuracy (%): 77.0 -> 92.2 | Improved |
| add the color branch (ablation) | CoDA image branch · FakeForm Cartoon (B&W) | accuracy (%): 66.9 -> 68.2 | Improved |
| increase noise replicas R from 20 to 50 (ablation) | CoDA · FakeForm 62 domains | accuracy (%): 75.7 -> 77.7 | Improved |
| raise noise level sigma from 0.05 to 0.10 (ablation) | CoDA · FakeForm 62 domains | accuracy (%): 75.1 -> 77.7 | Improved |
| raise noise level sigma from 0.10 to 0.20 (ablation) | CoDA · FakeForm 62 domains | accuracy (%): 77.7 -> 75.3 | Hurt |
| replace CLIP backbone with ResNet (both with color branch) (ablation) | CoDA · FakeForm 62 domains | accuracy (%): 76.9 -> 77.7 | Improved |
| add the color branch to CLIP (ablation) | CLIP Only · FakeForm 62 domains | accuracy (%): 75.2 -> 76.9 | Improved |
| apply JPEG compression QF=75 to test images | CoDA · GenImage-style diffusion test | accuracy (%): 95.3 -> 93.7 | Hurt |
Closest papers by meaning
- Secret Lies in Color: Enhancing AI-Generated Images Detection with Color Distribution Analysis (CVPR 2025 · similarity 0.90)
- CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI (CVPR 2025 · similarity 0.87)
- WildFake: A Large-Scale and Hierarchical Dataset for AI-Generated Images Detection (AAAI 2025 · similarity 0.86)
- Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection (ICML 2025 · similarity 0.86)
- A Bias-Free Training Paradigm for More General AI-generated Image Detection (CVPR 2025 · similarity 0.86)
- Few-Shot Learner Generalizes Across AI-Generated Image Detection (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
