Monkey Transfer Learning Can Improve Human Pose Estimation

TL;DR

This paper demonstrates that transfer learning from macaque monkey pose data can enhance human pose estimation accuracy, especially in clinical contexts with limited human data.

Contribution

It introduces a novel transfer learning approach from monkey to human pose estimation, improving performance with fewer human training examples.

Findings

Transfer learning from monkeys improves human pose estimation accuracy.

Fewer human training samples are needed with monkey data (1,000 vs 19,185).

Enhanced generalisability to clinical populations with pathological movements.

Abstract

In this study, we investigated whether transfer learning from macaque monkeys could improve human pose estimation. Current state-of-the-art pose estimation techniques, often employing deep neural networks, can match human annotation in non-clinical datasets. However, they underperform in novel situations, limiting their generalisability to clinical populations with pathological movement patterns. Clinical datasets are not widely available for AI training due to ethical challenges and a lack of data collection. We observe that data from other species may be able to bridge this gap by exposing the network to a broader range of motion cues. We found that utilising data from other species and undertaking transfer learning improved human pose estimation in terms of precision and recall compared to the benchmark, which was trained on humans only. Compared to the benchmark, fewer human training examples were needed for the transfer learning approach (1,000 vs 19,185). These results suggest that macaque pose estimation can improve human pose estimation in clinical situations. Future work should further explore the utility of pose estimation trained with monkey data in clinical populations.