Research map / Label-efficient and robust learning / Semi-supervised learning
Aggregation via Separation: Boosting Facial Landmark Detector With Semi-Supervised Style Translation
Shengju Qian, Keqiang Sun, Wayne Wu, Chen Qian, Jiaya Jia
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 style-translation augmentation | SAN · WFLW fullset | NME (%): 5.22 -> 4.39 | Improved |
| add style-translation augmentation | LAB · WFLW fullset | NME (%): 5.27 -> 4.76 | Improved |
| add style-translation augmentation | Res-18 · WFLW fullset | NME (%): 6.09 -> 5.25 | Improved |
| add style-translation augmentation | SAN · AFLW-68 full set | NME (%): 6.94 -> 6.01 | Improved |
| add style-translation augmentation | Res-18 · AFLW-68 full set | NME (%): 7.23 -> 7.17 | No clear effect |
| add style-translation augmentation on 10% of training data | Res-18 · 300W | NME (%): 13.72 -> 7.86 | Improved |
| add style-translation augmentation on 10% of training data | SAN · WFLW | NME (%): 9.16 -> 7.2 | Improved |
| increase number of random styles k from 0 to 8 (ablation) | Ours with ResNet-50 · WFLW test set | NME (%): 6.22 -> 5.31 | Improved |
| increase number of random styles k from 16 to 32 (ablation) | Ours with ResNet-50 · WFLW test set | NME (%): 5.29 -> 5.34 | Hurt |
| add KL divergence loss to the disentangling model (ablation) | Ours · WFLW test set | NME (%): 9.08 -> 7.98 | Improved |
| add perceptual loss to the disentangling model (ablation) | Ours · WFLW test set | NME (%): 8.34 -> 7.98 | Improved |
| replace Res-18 with SAN backbone under style augmentation | Ours · WFLW fullset | NME (%): 5.25 -> 4.39 | Improved |
Closest papers by meaning
- Style Aggregated Network for Facial Landmark Detection (CVPR 2018 · similarity 0.92)
- PriSM: Parsing and Style-Mixed Consistency for Unsupervised Domain Adaptation in Facial Landmark Detection (ECCV 2026 · similarity 0.90)
- Facial Landmark Detection: A Literature Survey (IJCV 2018 · similarity 0.90)
- Brute-Force Facial Landmark Analysis With a 140,000-Way Classifier (AAAI 2018 · similarity 0.90)
- Generalizable Face Landmarking Guided by Conditional Face Warping (CVPR 2024 · similarity 0.87)
- LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition (CVPR 2024 · 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.
