Research map / Detection and segmentation / Open-set and few-shot detection
ObjectFormer for Image Manipulation Detection and Localization
Junke Wang, Zuxuan Wu, Jingjing Chen, Xintong Han, Abhinav Shrivastava, Ser-Nam Lim, Yu-Gang Jiang
Check 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 |
|---|---|---|---|
| Use ObjectFormer instead of PSCCNet | Image manipulation localization · Coverage, fine-tuned | localization AUC (%): 94.1 -> 95.7 | Improved |
| Use ObjectFormer instead of PSCCNet | Image manipulation localization · CASIA, fine-tuned | localization AUC (%): 87.5 -> 88.2 | Improved |
| Use ObjectFormer instead of PSCCNet | Image manipulation localization · NIST16, fine-tuned | localization AUC (%): 99.6 -> 99.6 | No clear effect |
| Use ObjectFormer instead of PSCCNet | Image manipulation detection · CASIA-D | detection AUC (%): 99.65 -> 99.70 | Improved |
| Add high-frequency feature extraction (ablation) | ObjectFormer · CASIA | localization AUC (%): 14.6% | Improved |
| Add high-frequency feature extraction (ablation) | ObjectFormer · NIST16 | localization AUC (%): 11.0% | Improved |
| Add boundary-sensitive contextual incoherence modeling (BCIM) (ablation) | ObjectFormer · CASIA | localization AUC (%): 6.2% | Improved |
| Add boundary-sensitive contextual incoherence modeling (BCIM) (ablation) | ObjectFormer · NIST16 | localization AUC (%): 2.4% | Improved |
| Use object prototypes and stacked object encoders/patch decoders rather than vanilla self-attention blocks (ablation) | ObjectFormer · NIST16 | localization AUC (%): 5% | Improved |
| Use object prototypes and stacked object encoders/patch decoders rather than vanilla self-attention blocks (ablation) | ObjectFormer · NIST16 | localization F1 (%): 12.5% | Improved |
| Increase the number of object prototypes, with the best reported setting at N=16 (ablation) | ObjectFormer · Columbia and CASIA | localization performance | Improved |
Closest papers by meaning
- UnionFormer: Unified-Learning Transformer with Multi-View Representation for Image Manipulation Detection and Localization (CVPR 2024 · similarity 0.90)
- Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods (CVPR 2024 · similarity 0.88)
- FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models (ICLR 2025 · similarity 0.88)
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.88)
- Training-Free Image Manipulation Localization Using Diffusion Models (AAAI 2025 · similarity 0.85)
- Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization (NeurIPS 2026 · similarity 0.85)
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.
