Cross-Species Transfer Learning in Agricultural AI: Evaluating ZebraPose Adaptation for Dairy Cattle Pose Estimation
This addresses the problem of limited annotated datasets for livestock pose estimation in agricultural AI, though it reveals that cross-species transfer is insufficient for robust deployment.
This study evaluated cross-species transfer learning by adapting ZebraPose, a vision transformer model trained on synthetic zebra imagery, for 27-keypoint pose estimation in dairy cows, achieving promising performance (AP = 0.86, AR = 0.87, PCK 0.5 = 0.869) on in-distribution data but showing substantial generalization failures in unseen barns and cow populations.
Pose estimation serves as a cornerstone of computer vision for understanding animal posture, behavior, and welfare. Yet, agricultural applications remain constrained by the scarcity of large, annotated datasets for livestock, especially dairy cattle. This study evaluates the potential and limitations of cross-species transfer learning by adapting ZebraPose - a vision transformer-based model trained on synthetic zebra imagery - for 27-keypoint detection in dairy cows under real barn conditions. Using three configurations - a custom on-farm dataset (375 images, Sussex, New Brunswick, Canada), a subset of the APT-36K benchmark dataset, and their combination, we systematically assessed model accuracy and generalization across environments. While the combined model achieved promising performance (AP = 0.86, AR = 0.87, PCK 0.5 = 0.869) on in-distribution data, substantial generalization failures occurred when applied to unseen barns and cow populations. These findings expose the synthetic-to-real domain gap as a major obstacle to agricultural AI deployment and emphasize that morphological similarity between species is insufficient for cross-domain transfer. The study provides practical insights into dataset diversity, environmental variability, and computational constraints that influence real-world deployment of livestock monitoring systems. We conclude with a call for agriculture-first AI design, prioritizing farm-level realism, cross-environment robustness, and open benchmark datasets to advance trustworthy and scalable animal-centric technologies.