Are CLIP Features All You Need for Universal Synthetic Image Origin Attribution?
- 12 May 2025
- book chapter
- Published by Springer Nature
- p. 363-382
Abstract
No abstract availableKeywords
All Related Versions
This publication has 45 references indexed in Scilit:
- Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection2024
- One-Shot Neural Face Reenactment via Finding Directions in GAN’s Latent SpaceInternational Journal of Computer Vision, 2024
- Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis2023
- RepMix: Representation Mixing for Robust Attribution of Synthesized Images2022
- ViM: Out-Of-Distribution with Virtual-logit Matching2022
- Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions2020
- Open Set Learning with Counterfactual Images2018
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009
- On the limited memory BFGS method for large scale optimizationMathematical Programming, 1989