Research map / Detection and segmentation / CNN features
Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs
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 |
|---|---|---|---|
| Use scale-associated side-output supervision and scale-specific fusion instead of HED's shared-scale side outputs and fusion | VGG-16 FCN for skeleton extraction · SK506 | F-measure: 0.542 -> 0.623 | Helped |
| Use scale-associated side-output supervision and scale-specific fusion instead of HED's shared-scale side outputs and fusion | VGG-16 FCN for skeleton extraction · WH-SYMMAX | F-measure: 0.732 -> 0.769 | Helped |
| Train with scale-associated side outputs and scale-specific fusion rather than HED | Skeleton extraction model trained on SK506 · SK506/WH-SYMMAX | F-measure: 0.637 -> 0.692 | Helped |
| Train with scale-associated side outputs and scale-specific fusion rather than HED | Skeleton extraction model trained on WH-SYMMAX · WH-SYMMAX/SK506 | F-measure: 0.492 -> 0.529 | Helped |
Closest papers by meaning
- Multi-Scale Bidirectional FCN for Object Skeleton Extraction (AAAI 2018 · similarity 0.90)
- DeepFlux for Skeletons in the Wild (CVPR 2019 · similarity 0.89)
- Feature Pyramid Networks for Object Detection (CVPR 2017 · similarity 0.86)
- A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images (CVPR 2019 · similarity 0.85)
- Straight to Shapes: Real-Time Detection of Encoded Shapes (CVPR 2017 · similarity 0.85)
- An Analysis of Scale Invariance in Object Detection SNIP (CVPR 2018 · 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.