Research map / Label-efficient and robust learning / Recognition and long-tail
Learning to Localize Little Landmarks
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 three sequential prediction steps rather than two (ablation) | latent-landmark localization · Car Door Handle Dataset | detection rate at normalized distance 0.02: 63.3 -> 74.4 | Helped |
| use sequential prediction rather than one prediction step (ablation) | latent-landmark localization · Car Door Handle Dataset | detection rate at normalized distance 0.02: 54.3 -> 74.4 | Helped |
| predict through latent landmarks rather than directly detect the target (ablation) | car door handle localization · Car Door Handle Dataset | detection rate at normalized distance 0.02: 19.2 -> 74.4 | Helped |
| use three sequential prediction steps rather than two (ablation) | latent-landmark localization · Light Switch Dataset | detection rate at normalized distance 0.5: 47.5 -> 51.0 | Helped |
| use sequential prediction rather than one prediction step (ablation) | latent-landmark localization · Light Switch Dataset | detection rate at normalized distance 0.5: 44.5 -> 51.0 | Helped |
| use three-step latent-landmark prediction rather than direct detection (ablation) | light switch localization · Light Switch Dataset | detection rate at normalized distance 0.5: 41.0 -> 51.0 | Helped |
| learn a sequence of latent landmarks using only target-location supervision | beak localization · CUBS200 | PCP: 61.2 -> 64.1 | Helped |
| learn latent landmarks and prediction models end-to-end | landmark localization · Car Door Handle Dataset and Light Switch Dataset | detection rate | Helped |
Closest papers by meaning
- Improving Landmark Localization With Semi-Supervised Learning (CVPR 2018 · similarity 0.88)
- Mechanisms of Object Localization in Vision-Language Models (CVPR 2026 · similarity 0.83)
- Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction (ICLR 2025 · similarity 0.83)
- LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D (ICML 2025 · similarity 0.83)
- Learning Object State Changes in Videos: An Open-World Perspective (CVPR 2024 · similarity 0.82)
- Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery (CVPR 2024 · similarity 0.82)
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.