Research map / Detection and segmentation / Open-set and few-shot detection
HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network
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 |
|---|---|---|---|
| Add VAF to the capsule autoencoder (ablation) | HP-Capsule subpart discovery · BP4D | NCD: 30.72 -> 19.27 | Helped |
| Add VAF to the capsule autoencoder (ablation) | HP-Capsule subpart discovery · BP4D | NME_DL (%) | Helped |
| Add TPM to aggregate the VAF-discovered subparts (ablation) | HP-Capsule · BP4D | NCD: 19.27 -> 18.79 | Helped |
| Add TPM to aggregate the VAF-discovered subparts (ablation) | HP-Capsule · BP4D | NME_DL (%): 6.21 -> 6.10 | Helped |
| Use HP-Capsule instead of SCOPS | Unsupervised face segmentation · BP4D | NME_L (N_GT=5) (%): 9.10 -> 8.81 | Helped |
| Use HP-Capsule instead of SCOPS | Unsupervised face segmentation · BP4D | NME_L (N_GT=68) (%): 9.67 -> 9.11 | Helped |
| Use HP-Capsule instead of SCOPS | Unsupervised face segmentation · BP4D | NME_DL (%): 6.74 -> 6.10 | Helped |
| Use HP-Capsule instead of SCOPS | Unsupervised face segmentation · Multi-PIE | NME_L (N_GT=5) (%): 16.15 -> 12.34 | Helped |
| Use HP-Capsule instead of SCOPS | Unsupervised face segmentation · Multi-PIE | NME_L (N_GT=68) (%): 15.25 -> 12.30 | Helped |
| Use HP-Capsule instead of SCOPS | Unsupervised face segmentation · Multi-PIE | NME_DL (%): 13.54 -> 11.57 | Helped |
Closest papers by meaning
- Graphics Capsule: Learning Hierarchical 3D Face Representations From 2D Images (CVPR 2023 · similarity 0.90)
- ParseCaps: An Interpretable Parsing Capsule Network for Medical Image Diagnosis (AAAI 2025 · similarity 0.85)
- SegFace: Face Segmentation of Long-Tail Classes (AAAI 2025 · similarity 0.85)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.83)
- OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning (CVPR 2024 · similarity 0.83)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.83)
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.