RNSIDNet detects synthetic images by using CLIP RGB features to dynamically modulate Bayar-convolution noise residuals, trained with a hard-sample-aware contrastive loss.
Towards universal fake image detectors that generalize across generative models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Benchmarks Vision Mamba variants for AI-generated image detection against CNN, ViT, and VLM detectors on diverse datasets and synthetic sources, reporting promise alongside limitations.
citing papers explorer
-
Generalized Synthetic Image Detection with Enhanced RGB-Noise Representation Learning
RNSIDNet detects synthetic images by using CLIP RGB features to dynamically modulate Bayar-convolution noise residuals, trained with a hard-sample-aware contrastive loss.
-
Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation
Benchmarks Vision Mamba variants for AI-generated image detection against CNN, ViT, and VLM detectors on diverse datasets and synthetic sources, reporting promise alongside limitations.