Research map / Image generation / Editing and style transfer
Towards Open-Set Identity Preserving Face Synthesis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 identity feature matching loss L_GC (ablation) | Open-Set Identity Preserving GAN · MS-Celeb-1M | Top-1 accuracy: 5.71 -> 81.11 | Helped |
| Add identity feature matching loss L_GC (ablation) | Open-Set Identity Preserving GAN · Multi-PIE | Top-1 accuracy: 11.76 -> 96.80 | Helped |
| Add transformation training (ablation) | Open-Set Identity Preserving GAN · MS-Celeb-1M | Top-1 accuracy: 79.19 -> 81.11 | Helped |
| Add transformation training (ablation) | Open-Set Identity Preserving GAN · Multi-PIE | Top-1 accuracy: 95.47 -> 96.80 | Helped |
| Add discriminator feature matching loss L_GD (ablation) | Open-Set Identity Preserving GAN · MS-Celeb-1M | Top-1 accuracy: 80.52 -> 81.11 | Helped |
| Add discriminator feature matching loss L_GD (ablation) | Open-Set Identity Preserving GAN · Multi-PIE | Top-1 accuracy: 95.53 -> 96.80 | Helped |
| Add unlabeled-data training (ablation) | Open-Set Identity Preserving GAN · MS-Celeb-1M | Top-1 accuracy: 80.24 -> 81.11 | Helped |
| Add unlabeled-data training (ablation) | Open-Set Identity Preserving GAN · Multi-PIE | Top-1 accuracy: 96.41 -> 96.80 | Helped |
| Add KL divergence regularization to the attribute vector (ablation) | Attribute encoder · FaceScrub validation | Top-1 identity classification accuracy from attribute vectors | Helped |
Closest papers by meaning
- FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network (AAAI 2025 · similarity 0.90)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.89)
- Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion (CVPR 2025 · similarity 0.88)
- Non-Adaptive Adversarial Face Generation (NeurIPS 2025 · similarity 0.87)
- Generative Unlearning for Any Identity (CVPR 2024 · similarity 0.87)
- UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition (ICLR 2025 · similarity 0.86)
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.