Research map / Detection and segmentation / CNN features
Handcrafted Outlier Detection Revisited
Luca Cavalli, Viktor Larsson, Martin Ralf Oswald, Torsten Sattler, Marc Pollefeys
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 |
|---|---|---|---|
| add side-information (orientation/scale) filtering (ablation) | AdaLAM · TUM | AUC@5: 22.4 -> 24.7 | Improved |
| add side-information (orientation/scale) filtering (ablation) | AdaLAM · YFCC100M | AUC@5: 54.5 -> 57.8 | Improved |
| add side-information filtering (ablation) | AdaLAM · TUM | runtime: 42ms -> 26ms | Improved |
| add adaptive thresholding (ablation) | AdaLAM · TUM | AUC@5: 22.4 -> 24.7 | Improved |
| add adaptive thresholding (ablation) | AdaLAM · YFCC100M | AUC@5: 57.5 -> 57.8 | Improved |
| add adaptive thresholding (ablation) | AdaLAM · TUM | runtime: 17ms -> 26ms | Hurt |
| add affine refitting on final inliers (ablation) | AdaLAM · TUM | AUC@5: 23.8 -> 24.7 | Improved |
| add affine refitting on final inliers (ablation) | AdaLAM · YFCC100M | AUC@5: 57.0 -> 57.8 | Improved |
| add refit and adaptive thresholding together (ablation) | AdaLAM · TUM | AUC@5: 24.4 -> 24.7 | Improved |
| add refit and adaptive thresholding together (ablation) | AdaLAM · YFCC100M | AUC@5: 57.8 -> 57.8 | No clear effect |
| add refit and adaptive thresholding together (ablation) | AdaLAM · YFCC100M | runtime: 26ms -> 40ms | Hurt |
| use 10x more LO-RANSAC iterations for ratio test (10k -> 100k) | Ratio test · TUM | AUC@5: 16.1 -> 17.3 | Improved |
Closest papers by meaning
- E3 Outlier: a Self-Supervised Framework for Unsupervised Deep Outlier Detection (TPAMI 2022 · similarity 0.88)
- Efficient Large Scale Inlier Voting for Geometric Vision Problems (ICCV 2021 · similarity 0.87)
- Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection (ICLR 2025 · similarity 0.86)
- RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples (ICML 2024 · similarity 0.86)
- LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data (AAAI 2025 · similarity 0.85)
- Quantile-Based Maximum Likelihood Training for Outlier Detection (AAAI 2024 · 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.
