Research map / Label-efficient and robust learning / Recognition and long-tail
Information Bottleneck Disentanglement for Identity Swapping
Gege Gao, Huaibo Huang, Chaoyou Fu, Zhaoyang Li, Ran He
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 |
|---|---|---|---|
| Add the Informative Identity Bottleneck (IIB) (ablation) | InfoSwap · FaceForensics++ | cosine similarity with source: 0.529 ± 0.118 -> 0.633 ± 0.098 | Improved |
| Add the Informative Identity Bottleneck (IIB) (ablation) | InfoSwap · FaceForensics++ | ID retrieval (%): 96.3 -> 99.7 | Improved |
| Add Identity Contrastive Loss (ICL) rather than conventional identity loss (ablation) | InfoSwap · FaceForensics++ | cosine similarity with target: 0.244 ± 0.118 -> 0.077 ± 0.104 | Improved |
| Add Identity Contrastive Loss (ICL) rather than conventional identity loss (ablation) | InfoSwap · FaceForensics++ | cosine similarity with source: 0.544 ± 0.111 -> 0.633 ± 0.098 | Improved |
| Use the target information controller during integration (ablation) | InfoSwap · FaceForensics++ | cosine similarity with source: 0.550 ± 0.110 -> 0.633 ± 0.098 | Improved |
| Use the target information controller during integration (ablation) | InfoSwap · FaceForensics++ | ID retrieval (%): 98.5 -> 99.7 | Improved |
Closest papers by meaning
- Learning Disentangled Representation for One-Shot Progressive Face Swapping (TPAMI 2024 · similarity 0.90)
- Reinforced Disentanglement for Face Swapping without Skip Connection (ICCV 2023 · similarity 0.90)
- Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping (ECCV 2022 · similarity 0.89)
- Critical Forgetting-Based Multi-Scale Disentanglement for Deepfake Detection (AAAI 2025 · similarity 0.87)
- DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID (CVPR 2025 · similarity 0.85)
- Disguise without Disruption: Utility-Preserving Face De-identification (AAAI 2024 · 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.
