Research map / Image generation / GANs
The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection
Vladimir V. Kniaz, Vladimir Knyaz, Fabio Remondino
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add retoucher generator GR adversarial training (ablation) | MAG · CASIA v2.0 | mAP: 0.41 -> 0.74 | Improved |
| add retoucher generator GR adversarial training (ablation) | MAG · Columbia | mAP: 0.34 -> 0.69 | Improved |
| add retoucher generator GR adversarial training (ablation) | MAG · Realistic Tampering | mAP: 0.28 -> 0.50 | Improved |
| add retoucher generator GR adversarial training (ablation) | MAG · Carvalho | mAP: 0.20 -> 0.48 | Improved |
| add retoucher generator GR adversarial training (ablation) | MAG · FantasticReality | mAP: 0.27 -> 0.61 | Improved |
| multi-task training (splice, edge, class) instead of single task (ablation) | MAG · CASIA v2.0 | mAP: 0.12 -> 0.74 | Improved |
| multi-task training instead of single task (ablation) | MAG · Columbia | mAP: 0.11 -> 0.69 | Improved |
| multi-task training instead of single task (ablation) | MAG · Realistic Tampering | mAP: 0.17 -> 0.50 | Improved |
| multi-task training instead of single task (ablation) | MAG · Carvalho | mAP: 0.19 -> 0.48 | Improved |
| multi-task training instead of single task (ablation) | MAG · FantasticReality | mAP: 0.12 -> 0.61 | Improved |
Closest papers by meaning
- Reality Transform Adversarial Generators for Image Splicing Forgery Detection and Localization (ICCV 2021 · similarity 0.87)
- Fighting Fake News: Image Splice Detection via Learned Self-Consistency (ECCV 2018 · similarity 0.86)
- Generate, Segment, and Refine: Towards Generic Manipulation Segmentation (AAAI 2020 · similarity 0.86)
- Unsupervised holistic image generation from key local patches (ECCV 2018 · similarity 0.85)
- Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection (CVPR 2023 · similarity 0.84)
- Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints (ICCV 2019 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
