Research map / Image generation / Editing and style transfer
DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition
Chaoyou Fu, Xiang Wu, Yibo Hu, Huaibo Huang, Ran He
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 |
|---|---|---|---|
| add identity sampling from large-scale VIS data and pairwise identity loss (DVG-Face vs DVG) | DVG · Tufts Face | Rank-1 (%): 56.1 -> 75.7 | Improved |
| add angular orthogonal loss (ablation) | DVG-Face · Tufts Face | Rank-1 (%): 55.9 -> 75.7 | Improved |
| add pairwise identity preserving loss (ablation) | DVG-Face · Tufts Face | Rank-1 (%): 62.4 -> 75.7 | Improved |
| use identity sampler in both training and testing instead of LightCNN (ablation) | DVG-Face · Tufts Face | Rank-1 (%): 74.6 -> 75.7 | Improved |
| use generated data in addition to real data (ablation) | HFR network · Tufts Face | Rank-1 (%): 54.5 -> 75.7 | Improved |
| train on generated data only without real labeled data (ablation) | HFR network · Tufts Face | Rank-1 (%): 54.5 -> 36.6 | Hurt |
| use contrastive loss instead of pairwise distance loss on generated data (ablation) | DVG-Face · Tufts Face | Rank-1 (%): 70.3 -> 75.7 | Improved |
| introduce MS-Celeb-1M identities into generation instead of fine-tuning on MS-Celeb-1M images (ablation) | LightCNN · Tufts Face | Rank-1 (%): 33.9 -> 75.7 | Improved |
| increase generated pairs from 0 to 100K (ablation) | DVG-Face · Tufts Face | VR@FAR=1% (%): improved by 26.1% | Improved |
| increase generated pairs beyond 100K (ablation) | DVG-Face · Tufts Face | recognition performance | No clear effect |
| set lambda1 to 25 instead of 0 (ablation) | DVG-Face · Tufts Face | VR@FAR=1% (%): 43.6 -> 68.5 | Improved |
| set eta to 0.10 instead of 0 (ablation) | DVG-Face · Tufts Face | VR@FAR=1% (%): 46.5 -> 68.5 | Improved |
Closest papers by meaning
- Dual Variational Generation for Low Shot Heterogeneous Face Recognition (NeurIPS 2019 · similarity 0.97)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.87)
- UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition (ICLR 2025 · similarity 0.86)
- HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere (ICLR 2025 · similarity 0.86)
- UMFN: Unified Multi-Domain Face Normalization for Joint Cross-domain Prototype Learning and Heterogeneous Face Recognition (CVPR 2025 · similarity 0.86)
- $\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition (NeurIPS 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.
