Research map / Image generation / Autoregressive and latent generation
Dual-Branch Asymmetric Discrepancy Learning Based on Fake Image Pattern-Coexistence for AI-Generated Image Detection
Chunli Song, Jie Liu, Peiyang Wang, Ying Huang, Guixuan Zhang, Zhi Zeng, Shuwu Zhang
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 multi-scale (shallow + deep) AD loss to the CE baseline (ablation) | DADL · AIGCDetectBenchmark | ACCM: best AccM 94.71 | Improved |
| add shallow-feature AD loss alone to CE baseline (ablation) | DADL · AIGCDetectBenchmark | ACCM and APM | Improved |
| add deep-feature AD loss alone to CE baseline (ablation) | DADL · AIGCDetectBenchmark | ACCM and APM | Improved |
| vary loss weight lambda from 0.25 to 1.5 (ablation) | DADL · AIGCDetectBenchmark | ACCM and APM | No clear effect |
| use DADL on WFIR generator data | DADL · AIGCDetectBenchmark WFIR | accuracy: 52.82 vs 95.71 (AIGI-Holmes) | Hurt |
| train on All GenImage instead of single generator | DADL · Chameleon | accuracy: 59.35 -> 67.77 | Improved |
Closest papers by meaning
- Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection (ICML 2025 · similarity 0.89)
- CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI (CVPR 2025 · similarity 0.89)
- A Bias-Free Training Paradigm for More General AI-generated Image Detection (CVPR 2025 · similarity 0.88)
- Is Artificial Intelligence Generated Image Detection a Solved Problem? (NeurIPS 2025 · similarity 0.88)
- Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection (ICML 2025 · similarity 0.87)
- Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable (NeurIPS 2025 · similarity 0.87)
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.
