HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.
Dual data alignment makes ai- generated image detector easier generalizable
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
fields
cs.CV 8representative citing papers
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
Frozen features from vision foundation models enable a linear probe to outperform specialized AIGI detectors by over 30% on in-the-wild data due to emergent forgery knowledge from pre-training.
PiN-CLIP jointly trains a noise generator and detector under a variational positive-incentive principle to inject feature-space noise that suppresses shortcut directions and improves out-of-distribution accuracy by 5.4 points on images from 42 generative models.
DEAR prunes channel features whose activations align strongly with inpaint masks, retaining only those capturing genuine generative artifacts to improve robustness against post-processing and unseen generators.
FGINet uses a band-masked frequency encoder and layer-wise gated injection to fuse frequency artifacts with vision foundation model semantics, plus hyperspherical compactness learning, to achieve better generalization in AI-generated image detection.
LoRA-based pairwise training with distortion and size simulations boosts robust AIGI detection under severe distortions, placing third in the NTIRE challenge.