Research map / 3D vision / Human pose estimation
Cross-Domain Adaptation for Animal Pose Estimation
Jinkun Cao, Hongyang Tang, Hao-Shu Fang, Xiaoyong Shen, Cewu Lu, Yu-Wing Tai
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 human pose data to animal training (2k labels) (ablation) | AlphaPose · Animal pose test | mAP: 30.3 -> 51.5 | Improved |
| add human pose data to animal training (4k labels) (ablation) | AlphaPose · Animal pose test | mAP: 44.3 -> 62.3 | Improved |
| add domain adaptation network (2k labels) (ablation) | WS-CDA · Animal pose test | mAP: 51.5 -> 53.0 | Improved |
| add domain adaptation network (4k labels) (ablation) | WS-CDA · Animal pose test | mAP: 62.3 -> 63.1 | Improved |
| add unlabeled animal data without weighting factor (2k labels) (ablation) | WS-CDA · Animal pose test | mAP: 53.0 -> 45.7 | Hurt |
| add unlabeled animal data without weighting factor (4k labels) (ablation) | WS-CDA · Animal pose test | mAP: 63.1 -> 57.2 | Hurt |
| add reweighting factor RB (w2=10) with unlabeled animal data (2k labels) (ablation) | WS-CDA · Animal pose test | mAP: 45.7 -> 56.7 | Improved |
| add reweighting factor RB (w2=10) with unlabeled animal data (4k labels) (ablation) | WS-CDA · Animal pose test | mAP: 57.2 -> 65.7 | Improved |
| increase labeled animal instances from 2k to 4k | WS-CDA · Animal pose test | mAP: 56.7 -> 65.7 | Improved |
| use w2=10 instead of 1 (ablation) | WS-CDA · Unseen animal class: cat | mAP: 34.5 -> 39.2 | Improved |
| add PPLO on top of WS-CDA (ablation) | WS-CDA · Unseen animal class: cat | mAP: 39.2 -> 42.3 | Improved |
| add PPLO on top of WS-CDA (ablation) | WS-CDA · Unseen animal class: cow | mAP: 54.6 -> 57.3 | Improved |
Closest papers by meaning
- AP-10K: A Benchmark for Animal Pose Estimation in the Wild (NeurIPS 2021 · similarity 0.91)
- From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation (CVPR 2021 · similarity 0.91)
- A Unified Framework for Domain Adaptive Pose Estimation (ECCV 2022 · similarity 0.91)
- Probabilistic Prompt Distribution Learning for Animal Pose Estimation (CVPR 2025 · similarity 0.89)
- Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance (NeurIPS 2025 · similarity 0.86)
- UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning (AAAI 2024 · similarity 0.86)
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.
