Research map / Video / Video segmentation and tracking
Learning Dynamic Hierarchical Models for Anytime Scene Labeling
Buyu Liu, Xuming He
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 |
|---|---|---|---|
| learn dynamic policy (D-NM) instead of static-myopic action sequence (ablation) | anytime scene labeling · CamVid | cost for similar accuracy: 13% and 21% v.s. 28% and 55% | Improved |
| use learned policy instead of random action selection (ablation) | D-NM · CamVid | accuracy vs cost | Improved |
| add joint feature and model selection instead of fixed model with feature selection (F-SM) (ablation) | D-NM · CamVid | accuracy vs cost | Improved |
| use D-NM instead of S-M on Stanford Background (ablation) | anytime scene labeling · Stanford Background | cost for similar accuracy: 11% and 15% v.s. 25% and 28% | Improved |
| use D-NM instead of S-M (ablation) | anytime scene labeling · Stanford Background | pixel accuracy: 81.7 -> 83.0 | Improved |
| use D-NM instead of S-M (ablation) | anytime scene labeling · Siftflow | IOU: 35.8 -> 36.7 | Improved |
| use D-NM instead of S-M (ablation) | anytime scene labeling · Siftflow | pixel accuracy: 85.8 -> 85.8 | No clear effect |
| use D-NM at DCRF time budget instead of full-feature DCRF | scene labeling · CamVid | pixel accuracy: 83.2 -> 84.7 | Improved |
| use D-NM instead of HIM | scene labeling · CamVid | computation cost: similar accuracy with about 50% of its computation cost | Improved |
Closest papers by meaning
- Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering (CVPR 2016 · similarity 0.87)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.86)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.85)
- Segment Anything without Supervision (NeurIPS 2024 · similarity 0.85)
- Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation (NeurIPS 2025 · similarity 0.85)
- Semantic-aware SAM for Point-Prompted Instance Segmentation (CVPR 2024 · similarity 0.85)
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.
