Research map / Label-efficient and robust learning / Semi-supervised learning
Hierarchical Information Passing Based Noise-Tolerant Hybrid Learning for Semi-Supervised Human Parsing
Yunan Liu, Shanshan Zhang, Jian Yang, PongChi Yuen
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 hierarchical information passing with a 3-stage network (ablation) | HRNet human parsing · Extended PASCAL-Person-Part | mIoU: 69.45 -> 73.51 | Improved |
| Add bottom-up information passing alongside top-down passing (ablation) | HIPN · Extended PASCAL-Person-Part | mIoU: 73.15 -> 73.51 | Improved |
| Increase HIPN stages from 1 to 4 with top-down and bottom-up passing (ablation) | HIPN · Extended PASCAL-Person-Part | mIoU: 71.81 -> 73.66 | Improved |
| Add cross-level consistency to certainty-based noisy-label identification (ablation) | Hybrid learning for human parsing · Extended PASCAL-Person-Part | mIoU: 74.57 -> 74.91 | Improved |
| Use certainty-based noise identification instead of NLNL identification (ablation) | Hybrid learning for human parsing · Extended PASCAL-Person-Part | clean/noisy classification accuracy: 60.59 -> 63.81 | Improved |
| Replace positive learning with noise-tolerant hybrid learning (ablation) | Semi-supervised human parsing with 1/8 labeled LIP training data · LIP val | mIoU: 42.91 -> 43.54 | Improved |
| Replace positive learning with noise-tolerant hybrid learning (ablation) | Semi-supervised human parsing with 1/2 labeled LIP training data · LIP val | mIoU: 53.97 -> 54.69 | Improved |
| Add unlabeled training images and hybrid learning to HIPN | HIPN · LIP val | mIoU: 59.61 -> 60.81 | Improved |
| Add unlabeled test images and hybrid learning to HIPN | HIPN · Extended PASCAL-Person-Part test | mIoU: 73.51 -> 74.91 | Improved |
Closest papers by meaning
- From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing (TPAMI 2024 · similarity 0.88)
- Deep Learning Technique for Human Parsing: A Survey and Outlook (IJCV 2024 · similarity 0.88)
- Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains (CVPR 2023 · similarity 0.87)
- Self-Correction for Human Parsing (TPAMI 2020 · similarity 0.87)
- Blended Grammar Network for Human Parsing (ECCV 2020 · similarity 0.87)
- Progressive Cognitive Human Parsing (AAAI 2018 · similarity 0.87)
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.
