Papers with Code 아카이브
Synthetic Image Attribution
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
LoRAX: LoRA eXpandable Networks for Continual Synthetic Image Attribution
Present and Future Generalization of Synthetic Image Detectors
BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy
A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images
ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.