Modern vision foundation models plus a tunable attention pooling classifier head deliver state-of-the-art detection of AI-generated and inpainted images, outperforming CLIP by over 12 percent accuracy.
Gen- erating diverse high-fidelity images with vq-vae-2.Neural Information Processing Systems (NeurIPS), 2019
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TAP into the Patch Tokens: Leveraging Vision Foundation Model Features for AI-Generated Image Detection
Modern vision foundation models plus a tunable attention pooling classifier head deliver state-of-the-art detection of AI-generated and inpainted images, outperforming CLIP by over 12 percent accuracy.