Research map / Detection and segmentation / CNN features
Hierarchically Gated Deep Networks for Semantic Segmentation
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 |
|---|---|---|---|
| Remove the multi-layered gates between layers (ablation) | HGDN · Stanford Background | pixel-wise accuracy: 82.41 -> 63.84% | Hurt |
| Remove the multi-layered gates between layers (ablation) | HGDN · Stanford Background | label average accuracy: 72.98 -> 65.92% | Hurt |
| Remove the multi-layered gates between layers (ablation) | HGDN · SIFT Flow | pixel-wise accuracy: 79.68 -> 56.75% | Hurt |
| Remove the multi-layered gates between layers (ablation) | HGDN · SIFT Flow | label average accuracy: 51.26 -> 43.22% | Hurt |
Closest papers by meaning
- Attention to Scale: Scale-Aware Semantic Image Segmentation (CVPR 2016 · similarity 0.90)
- Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation (CVPR 2016 · similarity 0.89)
- Deep Hierarchical Semantic Segmentation (CVPR 2022 · similarity 0.89)
- Gated Fully Fusion for Semantic Segmentation (AAAI 2020 · similarity 0.89)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.87)
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · similarity 0.87)
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.