Research map / Detection and segmentation / CNN features
Towards Learning Structure via Consensus for Face Segmentation and Parsing
Check 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 |
|---|---|---|---|
| Replace pixel-wise cross-entropy with consensus loss (ablation) | COFW face segmentation · COFW test | IOU_face: 84.1 -> 85.7 | Helped |
| Replace pixel-wise cross-entropy with consensus loss (ablation) | COFW face segmentation · COFW test | spars.: 3.8 -> 1.6 | Helped |
| Add dropout and flip augmentation (ablation) | Structure via consensus on COFW · COFW test | IOU_face: 85.7 -> 87.0 | Helped |
| Train with random weights rather than transfer learning (ablation) | Softmax+CE face segmentation · COFW test | IOU_face: 84.5 -> 76.8 | Hurt |
| Replace pixel-wise loss with consensus loss (ablation) | Part Labels face parsing · Part Labels test | IOU_hair: 68.95 -> 72.48 | Helped |
| Replace pixel-wise loss with consensus loss (ablation) | Part Labels face parsing · Part Labels test | IOU_mean: 83.65 -> 85.74 | Helped |
| Add dropout and flip augmentation (ablation) | Part Labels baseline · Part Labels test | IOU_hair: 68.95 -> 73.97 | Helped |
| Add dropout and flip augmentation (ablation) | Structure via consensus on Part Labels · Part Labels test | IOU_hair: 72.48 -> 75.84 | Helped |
| Increase input resolution from 128 to 250 (ablation) | Structure via consensus on Part Labels · Part Labels test | acc_p: 96.05 -> 95.86 | Hurt |
Closest papers by meaning
- A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing (AAAI 2020 · similarity 0.88)
- SegFace: Face Segmentation of Long-Tail Classes (AAAI 2025 · similarity 0.88)
- Parameter Efficient Local Implicit Image Function Network for Face Segmentation (CVPR 2023 · similarity 0.88)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.86)
- Representation Rigidity in Face Embeddings: Orthogonal Identifiability and Backfill-Free Compatibility (NeurIPS 2026 · similarity 0.86)
- Robust Model-Based Face Reconstruction Through Weakly-Supervised Outlier Segmentation (CVPR 2023 · similarity 0.86)
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.