Research map / Detection and segmentation / Open-set and few-shot detection
Uncertainty-guided Learning for Improving Image Manipulation Detection
Kaixiang Ji, Feng Chen, Xin Guo, Yadong Xu, Jian Wang, Jingdong Chen
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 Uncertainty Estimation Network to vanilla IMD baseline (ablation) | HRNetV2 baseline · CASIA v1.0 | pixel-level F1: 59.7 -> 62.9 | Improved |
| add UEN to PSCC-Net with synthesized-data pretraining (ablation) | PSCC-Net · CASIA v1.0 | pixel-level F1: 55.1 -> 56.5 | Improved |
| add UEN to PSCC-Net with ImageNet init (ablation) | PSCC-Net · CASIA v1.0 | pixel-level F1: 52.5 -> 54.6 | Improved |
| add dynamic uncertainty supervision loss (ablation) | UEN · NIST16 | pixel-level F1: 91.8 -> 93.2 | Improved |
| add uncertainty-guided prediction refinement (ablation) | UEN · CASIA v1.0 | pixel-level AUC: 85.1 -> 87.7 | Improved |
| add UPR (ablation) | UEN · NIST16 | pixel-level F1: 92.1 -> 93.2 | Improved |
| include data uncertainty map in refinement (alpha>0 vs alpha=0, beta=1) | UEN · NIST16 with label noise above 30% | F1 | Improved |
| increase Monte Carlo sampling frequency T beyond 100 | UEN · CASIA | F1 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MVSS-Net — MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection (TPAMI 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A New Benchmark and Model for Challenging Image Manipulation Detection (AAAI 2024 · similarity 0.86)
- Epistemic Uncertainty for Generated Image Detection (NeurIPS 2025 · similarity 0.84)
- Training-Free Image Manipulation Localization Using Diffusion Models (AAAI 2025 · similarity 0.83)
- IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning (ICLR 2025 · similarity 0.83)
- UnionFormer: Unified-Learning Transformer with Multi-View Representation for Image Manipulation Detection and Localization (CVPR 2024 · similarity 0.83)
- Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization (NeurIPS 2026 · similarity 0.83)
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.
