computer-vision
Synthetic Image Attribution
3260 papers • 126 benchmarks • 313 datasets
Determine the source or origin of a generated image, such as identifying the model or tool used to create it. This information can be useful for detecting copyright infringement or for investigating digital crimes.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in synthetic-image-attribution
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find synthetic-image-attribution models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Artifact: A Large-Scale Dataset With Artificial And Factual Images For Generalizable And Robust Synthetic Image Detection
Md Awsafur Rahman, Bishmoy Paul, Najibul Haque Sarker, Z. Hakim, S. Fattah•Wed Feb 22 2023
This paper presents a large-scale dataset named ArtiFact, comprising diverse generators, object categories, and real-world challenges, and proposes a multi-class classification scheme that addresses social platform impairments and effectively detects synthetic images from both seen and unseen generators.
47