Research map / Detection and segmentation / CNN features
AdaIFL: Adaptive Image Forgery Localization via a Dynamic and Importance-aware Transformer Network
Yuxi Li, Fuyuan Cheng, Wangbo Yu, Guangshuo Wang, Guibo Luo, Yuesheng Zhu
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 feature importance-aware attention (FIA) instead of original attention (ablation) | AdaIFL · CASIA v1 | IoU: .609 -> .661 | Improved |
| add adaptive token aggregator (ATA) (ablation) | AdaIFL · MISD | IoU: .567 -> .606 | Improved |
| add dynamic expert groups in the encoder (DyE) (ablation) | AdaIFL · CASIA v1 | IoU: .587 -> .661 | Improved |
| add dynamic expert groups in the decoder (DyD) (ablation) | AdaIFL · MISD | IoU: .591 -> .606 | Improved |
| use AdaIFL instead of TruFor | image forgery localization · Mean over 5 datasets | IoU: .406 -> .472 | Improved |
| heavy Gaussian noise (k=23) applied to test images | AdaIFL · NIST16 distortions | IoU: .110 vs TruFor .119 | Hurt |
| AdaIFL on DSO-1 versus TruFor | AdaIFL · DSO-1 | IoU: .237 vs .270 | Hurt |
Closest papers by meaning
- SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints (AAAI 2025 · similarity 0.92)
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.90)
- Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization (AAAI 2025 · similarity 0.89)
- DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization (CVPR 2024 · similarity 0.88)
- A Lottery Ticket Hypothesis Approach with Sparse Fine-tuning and MAE for Image Forgery Detection and Localization (AAAI 2025 · similarity 0.88)
- ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization (NeurIPS 2025 · similarity 0.88)
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.
