Research map / Learning theory and algorithms / Prediction and decision losses
Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach
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 |
|---|---|---|---|
| Use the proposed unsupervised RL method instead of RANSAC or LO-RANSAC | 2D line fitting · Synthetic 2D line fitting | consensus size | Helped |
| Use the proposed unsupervised RL method instead of A* | 2D line fitting · Synthetic 2D line fitting | runtime | Helped |
| Use the proposed unsupervised RL method instead of random action selection | 3D plane fitting · Synthetic 3D plane fitting | solution quality | Helped |
| Use the proposed unsupervised RL method instead of A* methods | 3D plane fitting · Synthetic 3D plane fitting | runtime | Helped |
| Use the proposed unsupervised RL method instead of RANSAC-based methods | Fundamental matrix estimation · ModelNet40 | consensus size | Helped |
| Use the proposed unsupervised RL method instead of ULCM | Fundamental matrix estimation · ModelNet40 | consensus size | Helped |
| Use the proposed unsupervised RL method instead of ULCM | Fundamental matrix estimation · KITTI | consensus size | Helped |
| Use the proposed unsupervised RL method instead of RANSAC | Fundamental matrix estimation · KITTI | median consensus size | Helped |
| Test with twice as many points and higher outlier rates without retraining | Proposed method · Synthetic 2D line fitting | solution quality | No clear effect |
| Test with twice as many points and higher outlier rates without retraining | Proposed method · Synthetic 3D plane fitting | solution quality | No clear effect |
Closest papers by meaning
- Unsupervised Learning of Consensus Maximization for 3D Vision Problems (CVPR 2019 · similarity 0.87)
- Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning (CVPR 2022 · similarity 0.87)
- Robust Unsupervised Learning via L-statistic Minimization (ICML 2021 · similarity 0.86)
- Unsupervised Image Matching and Object Discovery as Optimization (CVPR 2019 · similarity 0.86)
- On the Provable Advantage of Unsupervised Pretraining (ICLR 2024 · similarity 0.85)
- LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders (NeurIPS 2025 · similarity 0.84)
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.