Research map / Optimization / Implicit bias and generalization
Facial Landmarks Detection by Self-Iterative Regression Based Landmarks-Attention Network
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 |
|---|---|---|---|
| Use one self-iterated regressor instead of cascaded regressors | Facial landmarks detection with LAN · 300-W public testing set | NME: 6.23 -> 5.04 | Helped |
| Use one self-iterated regressor instead of cascaded regressors | Facial landmarks detection with LAN · Pre-trained model | Number of parameters: 14.88M -> 3.72M | Helped |
| Use one self-iterated regressor instead of cascaded regressors | Facial landmarks detection with LAN · Pre-trained model | Model memory: 62.4MB -> 15.6MB | Helped |
| Use LAN instead of stacking all landmark patches for feature extraction (ablation) | SIR · 300-W competition testing set | Detection accuracy | Helped |
| Increase the number of self-iterations before stable performance (ablation) | SIR · Facial landmarks detection | Detection accuracy | Helped |
| Increase Gaussian sampling standard deviation (ablation) | SIR · 300-W public testing set | NME | Mixed |
| Use an appropriate Gaussian sampling standard deviation (ablation) | SIR · 300-W public testing set | NME | Helped |
Closest papers by meaning
- Towards Accurate Facial Landmark Detection via Cascaded Transformers (CVPR 2022 · similarity 0.90)
- A Deep Regression Architecture With Two-Stage Re-Initialization for High Performance Facial Landmark Detection (CVPR 2017 · similarity 0.88)
- Self-Reinforced Cascaded Regression for Face Alignment (AAAI 2018 · similarity 0.88)
- Continuous Landmark Detection With 3D Queries (CVPR 2023 · similarity 0.88)
- Dynamic Attention-Controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-Set Sample Weighting (CVPR 2017 · similarity 0.88)
- SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation (CVPR 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.