Research map / Detection and segmentation / CNN features
Contrastive Pseudo Learning for Open-World DeepFake Attribution
Zhimin Sun, Shen Chen, Taiping Yao, Bangjie Yin, Ran Yi, Shouhong Ding, Lizhuang Ma
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 |
|---|---|---|---|
| replace global relation loss with Global-Local Voting loss (ablation) | CPL · OW-DFA Protocol-1 (Novel) | ACC: 66.32 -> 68.16 | Improved |
| GLV loss on known classes (ablation) | CPL · OW-DFA Protocol-1 (Known) | ACC: 97.17 -> 96.64 | Hurt |
| add confidence-based soft pseudo-labeling to GR (ablation) | CE + GR · OW-DFA Protocol-1 (Novel) | NMI: 63.00 -> 67.72 | Improved |
| add CSP to GLV (ablation) | CPL · OW-DFA Protocol-1 (Novel) | ACC: 68.16 -> 71.89 | Improved |
| use plain pseudo-labeling instead of CSP (ablation) | CPL · OW-DFA Protocol-1 (All) | ACC: 81.54 -> 80.14 | Hurt |
| use threshold-based pseudo-labels (FixMatch/FlexMatch/FreeMatch) instead of CSP (ablation) | CPL · OW-DFA Protocol-1 (Novel) | ACC: 71.89 -> 66.16 to 67.74 | Hurt |
| use Gumbel-Softmax without confidence weight (ablation) | CPL · OW-DFA Protocol-1 (Novel) | ACC: 71.89 -> 68.27 | Hurt |
| add stage 3 iterative learning with semi-supervised k-means pseudo labels (ablation) | CPL · OW-DFA Protocol-1 (All) | ACC: 83.59 -> 84.20 | Improved |
| pretrain on labeled data before CPL (stage 1) (ablation) | CPL · OW-DFA Protocol-1 | ACC: 83.70 -> 83.59 (All ACC) | No clear effect |
| use CPL attribution training instead of multi-class training for real/fake detection | real/fake detector · Protocol-2 new fake + new real | AUC: 76.47 -> 85.97 | Improved |
Closest papers by meaning
- DF40: Toward Next-Generation Deepfake Detection (NeurIPS 2024 · similarity 0.89)
- FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge (NeurIPS 2024 · similarity 0.88)
- TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution (AAAI 2024 · similarity 0.88)
- From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes (NeurIPS 2025 · similarity 0.88)
- DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion (NeurIPS 2024 · similarity 0.88)
- FakeDiffer: Distributional Disparity Learning on Differentiated Reconstruction for Face Forgery Detection (AAAI 2025 · similarity 0.87)
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.
