Horse-10 is an animal pose estimation dataset. It comprises 30 diverse Thoroughbred horses, for which 22 body parts were labeled by an expert in 8,114 frames (animal pose estimation). Horses have various coat colors and the “in-the-wild” aspect of the collected data at various Thoroughbred yearling sales and farms added additional complexity. The authors introduce Horse-C to contrast the domain shift inherent in the Horse-10 dataset with domain shift induced by common image corruptions.
Variants: Horse-10
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Animal Pose Estimation | SuperAnimal-Quadruped HRNet-w32 | SuperAnimal pretrained pose estimation models … | 2022-03-14 |
| Animal Pose Estimation | mmpose HRNet-w32 (w/ImageNet pretrained weights) | SuperAnimal pretrained pose estimation models … | 2022-03-14 |
| Animal Pose Estimation | DeepLabCut-RESNET-101 | Pretraining boosts out-of-domain robustness for … | 2019-09-24 |
| Animal Pose Estimation | DeepLabCut-RESNET 50 | Pretraining boosts out-of-domain robustness for … | 2019-09-24 |
| Animal Pose Estimation | DeepLabCut-EfficientNet-B6 | Pretraining boosts out-of-domain robustness for … | 2019-09-24 |
| Animal Pose Estimation | DeepLabCut-MOBILENETV2 0.35 | Pretraining boosts out-of-domain robustness for … | 2019-09-24 |
| Animal Pose Estimation | DeepLabCut-MOBILENETV2-1 | Pretraining boosts out-of-domain robustness for … | 2019-09-24 |
| Animal Pose Estimation | DeepLabCut-EfficientNet-B4 | Pretraining boosts out-of-domain robustness for … | 2019-09-24 |
Recent papers with results on this dataset: