Pretraining boosts out-of-domain robustness for pose estimation

TL;DR

Pretraining on ImageNet significantly improves the robustness of neural networks for pose estimation across different animal species and under various domain shifts, including unseen horses and corrupted data.

Contribution

This study introduces a new horse dataset for robustness benchmarking and demonstrates that pretraining enhances out-of-domain generalization in pose estimation.

Findings

Pretraining improves performance on out-of-domain horse data.

Better ImageNet models generalize across animal species.

Pretraining increases robustness to common corruptions.

Abstract

Neural networks are highly effective tools for pose estimation. However, as in other computer vision tasks, robustness to out-of-domain data remains a challenge, especially for small training sets that are common for real-world applications. Here, we probe the generalization ability with three architecture classes (MobileNetV2s, ResNets, and EfficientNets) for pose estimation. We developed a dataset of 30 horses that allowed for both "within-domain" and "out-of-domain" (unseen horse) benchmarking - this is a crucial test for robustness that current human pose estimation benchmarks do not directly address. We show that better ImageNet-performing architectures perform better on both within- and out-of-domain data if they are first pretrained on ImageNet. We additionally show that better ImageNet models generalize better across animal species. Furthermore, we introduce Horse-C, a new benchmark for common corruptions for pose estimation, and confirm that pretraining increases performance in this domain shift context as well. Overall, our results demonstrate that transfer learning is beneficial for out-of-domain robustness.