Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Structured Regression Gradient Boosting
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 |
|---|---|---|---|
| add structured GCRF weak learners to gradient boosting | gradient boosting for vessel segmentation · DRIVE test | F-measure: 80.61 -> 80.91 | Helped |
| add neighboring-variable information through derivative filters (ablation) | SRGB · DRIVE test, stage 1 | F-measure: 78.82 -> 79.53 | Helped |
| add diagonal derivative filters (ablation) | SRGB · DRIVE test, stage 1 | F-measure: 79.53 -> 79.70 | Helped |
| add shift operators to the filter set (ablation) | SRGB · DRIVE test, stage 1 | F-measure: 79.70 -> 79.54 | Hurt |
| learn the influence among filter responses jointly rather than independently (ablation) | SRGB · DRIVE test, stage 1 | F-measure: 79.53 -> 78.93 | Hurt |
| add pairwise neighborhood filters (ablation) | SRGB · Make3D test | rms: 11.76 -> 11.65 | Helped |
| add nonlocal neighborhood filters (ablation) | SRGB · Make3D test | rms: 11.76 -> 11.48 | Helped |
| add nonlocal neighborhood filters (ablation) | SRGB · Make3D test | rel: 0.309 -> 0.315 | Hurt |
| use structured GCRF boosting rather than the unstructured gradient-boosting baseline | gradient boosting · Chinese character small-occlusion inpainting | accuracy: 77.66 -> 79.87 | Helped |
| add 4-neighbor connections (ablation) | SRGB · Chinese character small-occlusion inpainting | accuracy: 77.66 -> 79.37 | Helped |
| add 8-neighbor connections (ablation) | SRGB · Chinese character small-occlusion inpainting | accuracy: 79.37 -> 79.87 | Helped |
Closest papers by meaning
- A Smoother Way to Train Structured Prediction Models (NeurIPS 2018 · similarity 0.85)
- Extending the Modelling Capacity of Gaussian Conditional Random Fields while Learning Faster (AAAI 2016 · similarity 0.85)
- Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization (NeurIPS 2025 · similarity 0.84)
- Statistical Inference for Gradient Boosting Regression (NeurIPS 2025 · similarity 0.83)
- Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling (ICML 2024 · similarity 0.83)
- Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness (NeurIPS 2025 · similarity 0.82)
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.