SOTAVerified

Image Attribution

Image attribution algorithms aim to identify important regions that are highly relevant to model decisions.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 26 papers

TitleStatusHype
Sampling Matters in Explanations: Towards Trustworthy Attribution Analysis Building Block in Visual Models through Maximizing Explanation Certainty—0
WILD: a new in-the-Wild Image Linkage Dataset for synthetic image attribution—0
LoRAX: LoRA eXpandable Networks for Continual Synthetic Image AttributionCode0
Are handcrafted filters helpful for attributing AI-generated images?—0
I2AM: Interpreting Image-to-Image Latent Diffusion Models via Attribution Maps—0
BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution—0
Hide and Seek: How Does Watermarking Impact Face Recognition?—0
Detecting Origin Attribution for Text-to-Image Diffusion ModelsCode0
Less is More: Fewer Interpretable Region via Submodular Subset SelectionCode2
A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic ImagesCode0
Show:102550
← PrevPage 1 of 3Next →
All datasetsCelebACUB-200-2011VGGFace2

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SMDL-Attribution (ICLR version)Insertion AUC score (ResNet-101)0.73—Unverified
2Grad-CAMInsertion AUC score (ResNet-101)0.72—Unverified
3RISEInsertion AUC score (ResNet-101)0.72—Unverified
4HSIC-AttributionInsertion AUC score (ResNet-101)0.68—Unverified
5LIMEInsertion AUC score (ResNet-101)0.68—Unverified
6Kernel SHAPInsertion AUC score (ResNet-101)0.68—Unverified
7SaliencyInsertion AUC score (ResNet-101)0.66—Unverified
8Integrated GradientsInsertion AUC score (ResNet-101)0.04—Unverified