AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

SynerDetect: Hierarchical Synergistic Learning for Generalizable AI-Generated Image Detection

Shuaibo Li, Yijun Yang, Zhaohu Xing, Hongqiu Wang, Pengfei Hao, Xingyu Li, Zekai Liu, Qing Zhang, Lei Zhu

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Cross-Model Interactive Distillation (generative reconstruction into perceptual encoder) (ablation)SynerDetect · AIGCDetectBenchmarkmean accuracy (%): 82.52 -> 94.76Improved
add OT-DCL fusion (ablation)SynerDetect · AIGCDetectBenchmarkmean accuracy (%): 85.41 -> 94.76Improved
add prototype-based optimal transport regularizer (ablation)SynerDetect OT-DCL · AIGCDetectBenchmarkmean accuracy (%): 87.24 -> 94.76Improved
use dedicated OT-DCL fusion instead of generic fusion or concatenation (ablation)SynerDetect · AIGCDetectBenchmarkmean accuracy (%): 74.02 (Fusion-B) -> 94.76Improved
combine perceptual and generative cues versus either alone (ablation)SynerDetect · AIGCDetectBenchmarkmean accuracy (%): 76.80 / 67.90 / 69.80 -> 94.76Improved
use simple feature concatenation of CLIP and diffusion features (ablation)SynerDetect · AIGCDetectBenchmarkmean accuracy (%): 76.80 (CLIP) -> 69.30Hurt
use learnable Visual-aware Tuner prompts instead of fixed text prompts (ablation)SynerDetect · AIGCDetectBenchmarkmean accuracy (%): 89.36 -> 94.76Improved
use both global visual embedding and local CConv features in prompt tuner (ablation)SynerDetect · AIGCDetectBenchmarkmean accuracy (%): 92.27 / 91.03 -> 94.76Improved
train SynerDetect on SD v1.4 and test on ChameleonSynerDetect · Chameleonaccuracy (%): 65.49 -> 71.02Improved
SynerDetect versus AIDE on GenImageSynerDetect · GenImagemean accuracy (%): 86.88 -> 92.39Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy