Research map / 3D vision / Face and shape
Self-Reinforced Cascaded Regression for Face Alignment
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 automatically labeled and selected unlabeled examples through self-reinforcement | LBF · LFPW test (224 images) | NME: 10.5 to 8.98 | Helped |
| Add automatically labeled and selected unlabeled examples through self-reinforcement | LBF · LFPW test | NME | Helped |
| Add automatically labeled and selected unlabeled examples through self-reinforcement | CFSS · LFPW test | NME | Helped |
| Select extra DAN training examples using self-reinforcement rather than selecting LBF predictions indiscriminately | DAN · Large dataset test (1,000 images) | NME | Helped |
| Increase the number of self-reinforced extra training examples from 400 to 900 (ablation) | DAN · Large dataset test (1,000 images) | NME: 400 to 900 | Helped |
| Use self-reinforcement rather than the original regressor alone, with only a small labeled subset | SR-LBF · 300W common subsets | NME | Mixed |
Closest papers by meaning
- Mnemonic Descent Method: A Recurrent Process Applied for End-To-End Face Alignment (CVPR 2016 · 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 0.85)
- FaceLift: Semi-supervised 3D Facial Landmark Localization (CVPR 2024 · similarity 0.84)
- Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model (CVPR 2025 · similarity 0.84)
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.