Research map / Label-efficient and robust learning / Semi-supervised learning
Learning From Synthetic Animals
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 CC-SSL with synthetic data and unlabeled real images instead of synthetic-only training | Animal keypoint estimation · TigDog horse | PCK@0.05 accuracy (mean): 25.33 -> 70.77 | Helped |
| Use CC-SSL with synthetic data and unlabeled real images instead of synthetic-only training | Animal keypoint estimation · TigDog tiger | PCK@0.05 accuracy (mean): 21.17 -> 64.14 | Helped |
| Use CC-SSL instead of BDL domain adaptation | Animal keypoint estimation · TigDog horse | PCK@0.05 accuracy (mean): 62.33 -> 70.77 | Helped |
| Use CC-SSL instead of BDL domain adaptation | Animal keypoint estimation · TigDog tiger | PCK@0.05 accuracy (mean): 52.26 -> 64.14 | Helped |
| Fine-tune CC-SSL with real image labels | CC-SSL · TigDog horse | PCK@0.05 accuracy (mean): 70.77 -> 82.43 | Helped |
| Fine-tune CC-SSL with real image labels | CC-SSL · TigDog tiger | PCK@0.05 accuracy (mean): 64.14 -> 84.00 | Helped |
| Add part segmentation as a joint training task (ablation) | Synthetic-data animal keypoint model · TigDog horse | PCK@0.05: 60.84 -> 62.25 | Helped |
| Add part segmentation as a joint training task (ablation) | Synthetic-data animal keypoint model · TigDog tiger | PCK@0.05: 50.26 -> 51.69 | Helped |
| Train on synthetic data with CC-SSL rather than real-labeled training | Animal keypoint estimation · VisDA2019 painting, tiger, visible keypoints | PCK@0.05 accuracy: 61.48 -> 55.78 | Hurt |
Closest papers by meaning
- Learning the 3D Fauna of the Web (CVPR 2024 · similarity 0.85)
- Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes (NeurIPS 2024 · similarity 0.84)
- Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding (NeurIPS 2024 · similarity 0.84)
- Reconstructing Animals and the Wild (CVPR 2025 · similarity 0.84)
- Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance (NeurIPS 2025 · similarity 0.84)
- OmniMotionGPT: Animal Motion Generation with Limited Data (CVPR 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.