Research map / Detection and segmentation / CNN features
Submodular Field Grammars: Representation, Inference, and Application to Image Parsing
Abram L. Friesen, Pedro M Domingos
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 |
|---|---|---|---|
| parse with a generated submodular field grammar instead of using DeepLab features alone | DeepLab · SBD test, 143 images | mean pixel accuracy: 87.77 -> 90.03 | Improved |
| replace a flat submodular MRF with an SFG over DeepLab features | DeepLab · SBD test, 143 images | mean pixel accuracy: 87.93 -> 90.03 | Improved |
| add a flat submodular MRF on top of DeepLab features | DeepLab · SBD test, 143 images | mean pixel accuracy: 87.77 -> 87.93 | No clear effect |
| use SFG-Parse instead of alpha-expansion and BP for MAP inference as boundary strength varies | SFG · synthetic SFGs, boundary scale factor | minimum energy and inference time | Improved |
| increase grammar height from SFG-Parse versus alpha-expansion and BP | SFG-Parse · synthetic SFGs, wBF 20 | inference time | Improved |
| increase number of productions per nonterminal, SFG-Parse versus alpha-expansion and BP | SFG-Parse · synthetic SFGs, wBF 20 | energy and inference time | Improved |
Closest papers by meaning
- Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering (CVPR 2016 · similarity 0.86)
- Single-View 3D Scene Reconstruction and Parsing by Attribute Grammar (TPAMI 2017 · similarity 0.86)
- Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image (ECCV 2018 · similarity 0.86)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.86)
- The Scene Language: Representing Scenes with Programs, Words, and Embeddings (CVPR 2025 · similarity 0.86)
- Compositional Scene Understanding through Inverse Generative Modeling (ICML 2025 · 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.
