Research map / Detection and segmentation / Open-set and few-shot detection
Few-Shot Keypoint Detection With Uncertainty Learning for Unseen Species
Changsheng Lu, Piotr Koniusz
Check 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 |
|---|---|---|---|
| Use FSKD with limb-interpolated auxiliary keypoints and multi-scale uncertainty-aware localization instead of the baseline | Few-shot keypoint detection · Animal Pose, unseen species, novel keypoints (Avg) | PCK@τ=0.1: 22.11 -> 44.75 | Improved |
| Use FSKD with limb-interpolated auxiliary keypoints and multi-scale uncertainty-aware localization instead of the baseline | Few-shot keypoint detection · CUB, unseen species, novel keypoints | PCK@τ=0.1: 66.12 -> 77.89 | Improved |
| Use FSKD with limb-interpolated auxiliary keypoints and multi-scale uncertainty-aware localization instead of the baseline | Few-shot keypoint detection · NABird, unseen species, novel keypoints | PCK@τ=0.1: 39.14 -> 56.04 | Improved |
| Use limb interpolation rather than random auxiliary-keypoint paths | FSKD · CUB, unseen species, novel keypoints | PCK@τ=0.1: 77.90 vs 77.89 | No clear effect |
| Add uncertainty-aware localization to the baseline (ablation) | FSKD · Animal Pose, CUB, and NABird, unseen species novel keypoints | PCK@τ=0.1: 22.11 -> 24.17; 66.12 -> 68.29; 39.14 -> 41.16 | Improved |
| Add auxiliary keypoints for training (ablation) | FSKD with UC-GBL · Animal Pose, CUB, and NABird, unseen species novel keypoints | PCK@τ=0.1: 24.17 -> 41.70; 68.29 -> 74.50; 41.16 -> 51.62 | Improved |
| Add multi-keypoint offset regression loss for grouped keypoints (ablation) | FSKD with UC-GBL and auxiliary keypoints · Animal Pose, CUB, and NABird, unseen species novel keypoints | PCK@τ=0.1: 41.70 -> 42.60; 74.50 -> 76.25; 51.62 -> 54.27 | Improved |
| Use multi-scale UC-GBL rather than single-scale UC-GBL at scale 8 (ablation) | FSKD with auxiliary keypoints · Animal Pose, CUB, and NABird, unseen species novel keypoints | PCK@τ=0.1: 42.60 -> 44.75; 76.25 -> 77.89; 54.27 -> 56.04 | Improved |
| Use HRNet-W48 rather than ResNet50 as the backbone (ablation) | FSKD (default) · Animal Pose, unseen species, novel keypoints (Avg) | PCK@τ=0.1: 44.75 -> 48.81 | Improved |
| Increase support examples from 1-shot to 5-shot (ablation) | FSKD (default) · Animal Pose, CUB, and NABird, unseen species novel keypoints | PCK@τ=0.1: 10.42%; 2.23%; 7.50% | Improved |
| Increase the number of base keypoint types used for training (ablation) | FSKD · CUB and NABird, novel keypoints | PCK@τ=0.1 | Improved |
| Use Gaussian pooling instead of integer indexing to extract keypoint features (ablation) | FSKD · Animal Pose, unseen cat and dog species | PCK@τ=0.1: 48.11 -> 52.36; 40.60 -> 47.94 | Improved |
Closest papers by meaning
- Detect Any Keypoints: An Efficient Light-Weight Few-Shot Keypoint Detector (AAAI 2024 · similarity 0.93)
- Exploiting Class-agnostic Visual Prior for Few-shot Keypoint Detection (IJCV 2026 · similarity 0.91)
- Open-Vocabulary Animal Keypoint Detection with Semantic-Feature Matching (IJCV 2024 · similarity 0.89)
- Semi-supervised Keypoint Localization (ICLR 2021 · similarity 0.89)
- Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features (CVPR 2024 · similarity 0.85)
- Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features (NeurIPS 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.
