Research map / Probabilistic and scientific modeling / Variational and generative sampling
Semi-crowdsourced Clustering with Deep Generative 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 noisy pairwise annotations to SCDC | SCDC · MNIST | accuracy: 65.92 ± 3.47 % -> 81.87 ± 3.86% | Helped |
| Add noisy pairwise annotations to SCDC | SCDC · MNIST | NMI: 0.6953 ± 0.0167 -> 0.7657 ± 0.0233 | Helped |
| Use BayesSCDC instead of SCDC | SCDC · MNIST without annotations | accuracy: 65.92 ± 3.47 % -> 77.64 ± 3.97 % | Helped |
| Use BayesSCDC instead of SCDC | SCDC · MNIST without annotations | time per epoch: 177.3s -> 11.2s | Helped |
| Use BayesSCDC instead of SCDC | SCDC · MNIST with annotations | accuracy: 81.87 ± 3.86% -> 84.24 ± 5.52% | Helped |
| Use BayesSCDC instead of SCDC | SCDC · MNIST with annotations | NMI: 0.7657 ± 0.0233 -> 0.8120 ± 0.0210 | Helped |
| Use BayesSCDC instead of SCDC | SCDC · MNIST with annotations | time per epoch: 201.7s -> 16.4s | Helped |
| Add noisy pairwise annotations to SCDC | SCDC · CIFAR-10 | NMI: 0.0424 ± 0.0119 -> 0.5549 ± 0.0028 | Helped |
| Add noisy pairwise annotations to SCDC | SCDC · CIFAR-10 | accuracy: 14.23 ± 0.69% -> 50.09 ± 0.08% | Helped |
| Add noisy annotations on a subset of items | BayesSCDC · Pinwheel, bad initialization | accuracy: 75.6% -> 96.6% | Helped |
| Add noisy annotations on a subset of items | BayesSCDC · Pinwheel, bad initialization | NMI: 0.806 -> 0.94 | Helped |
| Use SCDC instead of Deep MCVC | Deep MCVC · CIFAR-10 | NMI: 0.44 -> 0.55 | Helped |
Closest papers by meaning
- Semi-Supervised Learning From Crowds Using Deep Generative Models (AAAI 2018 · similarity 0.89)
- Multiple Clustering Views from Multiple Uncertain Experts (ICML 2017 · similarity 0.88)
- Deep Conditional Gaussian Mixture Model for Constrained Clustering (NeurIPS 2021 · similarity 0.88)
- Fairness, Semi-Supervised Learning, and More: A General Framework for Clustering with Stochastic Pairwise Constraints (AAAI 2021 · similarity 0.86)
- Samples Are Not Equal: A Sample Selection Approach for Deep Clustering (ICLR 2026 · similarity 0.86)
- KFNN: K-Free Nearest Neighbor For Crowdsourcing (NeurIPS 2024 · 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.