Research map / Detection and segmentation / CNN features
Holistically-Nested Edge Detection
Saining Xie, Zhuowen Tu
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 deep supervision on side outputs (ablation) | HED fusion-output · BSDS500 | AP: .738 -> .787 | Improved |
| add deep supervision on side outputs (ablation) | HED fusion-output · BSDS500 | ODS: .771 -> .782 | Improved |
| add deep supervision on side outputs (updated training) (ablation) | HED fusion-output · BSDS500 (updated training) | AP: .730 -> .811 | Improved |
| add deep supervision (updated training) (ablation) | HED fusion-output · BSDS500 (updated training) | ODS: .785 -> .790 | Improved |
| use HED topology instead of FCN-8s | edge detection net · BSDS500 | ODS: .697 -> .782 | Improved |
| use HED topology instead of FCN-2s with extra low-level links | edge detection net · BSDS500 | ODS: .738 -> .782 | Improved |
| average side outputs 1-5 instead of learned fusion (ablation) | HED · BSDS500 | AP: .787 -> .822 | Improved |
| merge fusion output with averaged side outputs (late merging) | HED · BSDS500 | AP: .787 -> .833 | Improved |
| include side-output 5 in average of side outputs 1-4 (ablation) | HED · BSDS500 | ODS: .760 -> .774 | Improved |
| add 100 extra training images | HED · BSDS500 | ODS: .782 -> .797 | Improved |
| use RGB and HHA depth encoding instead of raw depth channel or concatenation | HED · NYUD | ODS: .746 | Improved |
| retrain with scale augmentation and full-resolution images | HED · BSDS500 | ODS: .782 -> .790 | Improved |
Closest papers by meaning
- Deeply Supervised Salient Object Detection With Short Connections (CVPR 2017 · similarity 0.90)
- Richer Convolutional Features for Edge Detection (CVPR 2017 · similarity 0.87)
- Unsupervised Learning of Edges (CVPR 2016 · similarity 0.87)
- Learning to Predict Crisp Boundaries (ECCV 2018 · similarity 0.86)
- SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection (AAAI 2025 · similarity 0.84)
- DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection (AAAI 2024 · similarity 0.83)
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.
