Research map / Detection and segmentation / Open-set and few-shot detection
Instance-level Human Parsing via Part Grouping Network
Ke Gong, Xiaodan Liang, Yicheng Li, Yimin Chen, Ming Yang, Liang Lin
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 edge branch jointly (unified network) (ablation) | PGN segmentation · PASCAL-Person-Part | average IoU: 66.22 -> 66.91 | Improved |
| add refinement branch (ablation) | PGN · PASCAL-Person-Part | average IoU: 66.91 -> 68.40 | Improved |
| add segmentation branch jointly (ablation) | PGN edge · PASCAL-Person-Part edges | ODS: 41.8 -> 42.1 | Improved |
| add refinement branch (ablation) | PGN · PASCAL-Person-Part edges | ODS: 42.1 -> 42.5 | Improved |
| add refinement branch (ablation) | PGN · PASCAL-Person-Part edges | OIS: 43.5 -> 43.9 | Improved |
| joint training instead of two independent networks (ablation) | PGN · PASCAL-Person-Part instance parsing | AP^r_vol: 35.6 -> 37.8 | Improved |
| add refinement branch (ablation) | PGN · PASCAL-Person-Part instance parsing | AP^r_vol: 37.8 -> 39.2 | Improved |
| add grouping algorithm (ablation) | PGN · PASCAL-Person-Part instance parsing | AP^r_vol: 38.2 -> 39.2 | Improved |
| use full part-based grouping instead of large-area grouping (ablation) | PGN · PASCAL-Person-Part instance parsing | AP^r_vol: 38.6 -> 39.2 | Improved |
| add refinement branch (ablation) | PGN · CIHP | Mean IoU: 54.1 -> 55.8 | Improved |
| joint training instead of two independent networks (ablation) | PGN · CIHP | Mean IoU: 50.7 -> 54.1 | Improved |
| add grouping algorithm (ablation) | PGN · CIHP | AP^r_vol: 32.9 -> 33.6 | Improved |
Closest papers by meaning
- Differentiable Multi-Granularity Human Parsing (TPAMI 2023 · similarity 0.93)
- Look Into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing (CVPR 2017 · similarity 0.91)
- Part-Aware Context Network for Human Parsing (CVPR 2020 · similarity 0.91)
- Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing (CVPR 2021 · similarity 0.91)
- Parsing R-CNN for Instance-Level Human Analysis (CVPR 2019 · similarity 0.90)
- Deep Learning Technique for Human Parsing: A Survey and Outlook (IJCV 2024 · similarity 0.90)
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.
