Research map / Detection and segmentation / Open-set and few-shot detection
Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net
Fangting Xia, Peng Wang, Liang-Chieh Chen, Alan L. Yuille
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 the object-scale AZN (ablation) | HAZN (part-scale only) · PASCAL-Person-Part | mIOU (%): 54.78 -> 57.54 | Improved |
| add the part-scale AZN (ablation) | HAZN (object-scale only) · PASCAL-Person-Part | mIOU (%): 56.50 -> 57.54 | Improved |
| add object-scale AZN (ablation) | HAZN (part-scale only) · PASCAL-Person-Part (human size XS) | mIOU (%): 38.2 -> 47.1 | Improved |
| add part-scale AZN (ablation) | HAZN (object-scale only) · PASCAL-Person-Part (human size XS) | mIOU (%): 45.1 -> 47.1 | Improved |
| replace DeepLab-LargeFOV with HAZN | DeepLab-LargeFOV · PASCAL-Person-Part | mIOU (%): 51.78 -> 57.54 | Improved |
| replace DeepLab-LargeFOV with HAZN on small humans | DeepLab-LargeFOV · PASCAL-Person-Part (human size XS) | mIOU (%): 32.5 -> 47.1 | Improved |
| add CRF post-processing | DeepLab-LargeFOV · PASCAL-Person-Part | mIOU (%): 51.78 -> 52.95 | Improved |
| use auto-zoom instead of fixed multi-scale averaging | Multi-Scale Averaging · PASCAL-Person-Part | mIOU (%): 54.91 -> 57.54 | Improved |
| use auto-zoom instead of scale attention | Multi-Scale Attention · PASCAL-Person-Part | mIOU (%): 56.39 -> 57.54 | Improved |
| replace DeepLab-LargeFOV with HAZN for instance-wise parsing | DeepLab-LargeFOV · PASCAL-Person-Part | AP^r_part (%): 31.32 -> 43.72 | Improved |
| replace Multi-Scale Attention with HAZN for instance-wise parsing | Multi-Scale Attention · PASCAL-Person-Part | AP^r_part (%): 37.53 -> 43.72 | Improved |
| replace DeepLab-LargeFOV with HAZN on horses | DeepLab-LargeFOV · Horse-Cow (Horse) | mIOU avg: 66.25 -> 72.36 | Improved |
Closest papers by meaning
- Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer (CVPR 2018 · similarity 0.88)
- Instance-level Human Parsing via Part Grouping Network (ECCV 2018 · similarity 0.87)
- From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing (TPAMI 2024 · similarity 0.87)
- On the Correlation among Edge, Pose and Parsing (TPAMI 2021 · similarity 0.87)
- CDGNet: Class Distribution Guided Network for Human Parsing (CVPR 2022 · similarity 0.86)
- FLOAT: Factorized Learning of Object Attributes for Improved Multi-Object Multi-Part Scene Parsing (CVPR 2022 · 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.
