Research map / Architectures and efficiency / CNN design
Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
Read the paperCheck 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 |
|---|---|---|---|
| add the hierarchical multi-scale feature structure (ablation) | AMH-Net · NYUDv2 test (RGB) | ODS: .711 -> .722 | Helped |
| add AG-CRFs for multi-scale refinement and fusion (ablation) | AMH-Net · NYUDv2 test (RGB) | ODS: .722 -> .744 | Helped |
| add attention gating to the multi-scale CRF (ablation) | AMH-Net · NYUDv2 test (RGB) | ODS: .732 -> .744 | Helped |
| add intermediate deep-supervision losses (ablation) | AMH-Net · NYUDv2 test (RGB) | ODS: .725 -> .744 | Helped |
| use fully-latent rather than partially-latent AG-CRFs (ablation) | AMH-Net · NYUDv2 test (RGB) | AP: .746 -> .765 | Helped |
Closest papers by meaning
- Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation (CVPR 2018 · similarity 0.87)
- Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation (CVPR 2017 · similarity 0.87)
- Object Contour Detection With a Fully Convolutional Encoder-Decoder Network (CVPR 2016 · similarity 0.85)
- Gaussian Conditional Random Field Network for Semantic Segmentation (CVPR 2016 · similarity 0.85)
- Richer Convolutional Features for Edge Detection (CVPR 2017 · similarity 0.85)
- Attention to Scale: Scale-Aware Semantic Image Segmentation (CVPR 2016 · 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.