Research map / Detection and segmentation / CNN features
Learning Robust Facial Landmark Detection via Hierarchical Structured Ensemble
Xu Zou, Sheng Zhong, Luxin Yan, Xiangyun Zhao, Jiahuan Zhou, Ying Wu
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 HSLE structural constraints | HG baseline · 300W Full | mean iod-norm error: 3.77 -> 3.28 | Improved |
| add HSLE structural constraints | DU-Net baseline · 300W Full | mean iod-norm error: 3.47 -> 3.30 | Improved |
| add HSLE structural constraints | Merget et al. baseline · 300W Full | mean iod-norm error: 4.26 -> 3.70 | Improved |
| add HSLE structural constraints | Merget et al. baseline · 300W Challenge | mean iod-norm error: 5.69 -> 5.69 | No clear effect |
| add HSLE structural constraints | HG baseline · 300W Full | mean ipd-norm error: 5.27 -> 4.59 | Improved |
| add HSLE structural constraints | HG baseline · 300W Common | median iod-norm error: 3.17 -> 2.72 | Improved |
| add HSLE structural constraints | 4-stack hourglass · AFLW-Full | mean iod-norm error: 7.84 -> 7.52 | Improved |
| add HSLE structural constraints | 8-stack hourglass · AFLW-Full | mean iod-norm error: 7.64 -> 7.24 | Improved |
| replace manual bi-directional tree structure with learned HSLE (ablation) | 4-stack hourglass · AFLW-Full | mean iod-norm error: 7.64 -> 7.52 | Improved |
| replace manual bi-directional tree structure with learned HSLE (ablation) | 8-stack hourglass · AFLW-Full | mean iod-norm error: 7.56 -> 7.24 | Improved |
| increase number of ensembles from 4 to 8 (ablation) | HSLE-S4 · AFLW-Full | mean iod-norm error: 7.60 -> 7.47 | Improved |
| increase number of ensembles from 8 to 14 (ablation) | HSLE-S4 · AFLW-Full | mean iod-norm error: 7.47 -> 7.52 | No clear effect |
Closest papers by meaning
- Brute-Force Facial Landmark Analysis With a 140,000-Way Classifier (AAAI 2018 · similarity 0.88)
- Deep Structured Prediction for Facial Landmark Detection (NeurIPS 2019 · similarity 0.88)
- Learning to Detect 3D Facial Landmarks via Heatmap Regression with Graph Convolutional Network (AAAI 2022 · similarity 0.88)
- Facial Landmark Detection: A Literature Survey (IJCV 2018 · similarity 0.88)
- Heatmap Regression without Soft-Argmax for Facial Landmark Detection (ICCV 2025 · similarity 0.88)
- Facial Landmark Detection with Tweaked Convolutional Neural Networks (TPAMI 2017 · similarity 0.88)
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.
