NS-Net uses null-space projection on CLIP features plus contrastive learning and patch selection to improve generalization of AI-generated image detectors across 40 unseen generative models.
InProceedings of the Computer Vision and Pattern Recognition Conference, 23828–23837
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection
NS-Net uses null-space projection on CLIP features plus contrastive learning and patch selection to improve generalization of AI-generated image detectors across 40 unseen generative models.