Research map / Probabilistic and scientific modeling / Variational and generative sampling
Differentiable Learning of Submodular Models
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 graph cut (min-norm point) layer on top of CNN, trained end-to-end | CNN for horse segmentation · Weizmann horse segmentation (test, 0.1% labels) | accuracy: 0.8103 to 0.9121 | Helped |
| add graph cut (min-norm point) layer on top of CNN, trained end-to-end | CNN for horse segmentation · Weizmann horse segmentation (test, 0.1% labels) | NLL: 0.3919 to 0.2681 | Helped |
| add graph cut (min-norm point) layer on top of CNN, trained end-to-end | CNN for horse segmentation · Weizmann horse segmentation (test, 0.1% labels) | number of foreground objects (connected components): 96.9 to 25.3 | Helped |
Closest papers by meaning
- Provable Variational Inference for Constrained Log-Submodular Models (NeurIPS 2018 · similarity 0.90)
- Parameter Learning for Log-supermodular Distributions (NeurIPS 2016 · similarity 0.89)
- Variational Inference in Mixed Probabilistic Submodular Models (NeurIPS 2016 · similarity 0.88)
- From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular Models (ICML 2020 · similarity 0.88)
- Gradient Methods for Submodular Maximization (NeurIPS 2017 · similarity 0.88)
- Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems (NeurIPS 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.