Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913499295252480 |
|---|---|
| author | Otake, Hina Fukuhara, Yoshihiro Kubotani, Yoshiki Morishima, Shigeo |
| author_facet | Otake, Hina Fukuhara, Yoshihiro Kubotani, Yoshiki Morishima, Shigeo |
| contents | Are general-purpose visual representations acquired solely from synthetic data useful for detecting fake images? In this work, we show the effectiveness of synthetic data-driven representations for synthetic image detection. Upon analysis, we find that vision transformers trained by the latest visual representation learners with synthetic data can effectively distinguish fake from real images without seeing any real images during pre-training. Notably, using SynCLR as the backbone in a state-of-the-art detection method demonstrates a performance improvement of +10.32 mAP and +4.73% accuracy over the widely used CLIP, when tested on previously unseen GAN models. Code is available at https://github.com/cvpaperchallenge/detect-fake-with-fake. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08884 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection Otake, Hina Fukuhara, Yoshihiro Kubotani, Yoshiki Morishima, Shigeo Computer Vision and Pattern Recognition Machine Learning Are general-purpose visual representations acquired solely from synthetic data useful for detecting fake images? In this work, we show the effectiveness of synthetic data-driven representations for synthetic image detection. Upon analysis, we find that vision transformers trained by the latest visual representation learners with synthetic data can effectively distinguish fake from real images without seeing any real images during pre-training. Notably, using SynCLR as the backbone in a state-of-the-art detection method demonstrates a performance improvement of +10.32 mAP and +4.73% accuracy over the widely used CLIP, when tested on previously unseen GAN models. Code is available at https://github.com/cvpaperchallenge/detect-fake-with-fake. |
| title | Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2409.08884 |