Pretraining boosts out-of-domain robustness for pose estimation

Alexander Mathis, Mert Yüksekgönül, Byron Rogers, Matthias Bethge, Mackenzie W. Mathis

Keywords: pose estimation, robustness, out-of-domain, transfer learning

TL;DR: Transfer learning boosts out-of-domain robustness for pose estimation.

Abstract: Deep neural networks are highly effective tools for human and animal pose estimation. However, robustness to out-of-domain data remains a challenge. Here, we probe the transfer and generalization ability for pose estimation with two architecture classes (MobileNetV2s and ResNets) pretrained on ImageNet. We generated a novel dataset of 30 horses that allowed for both within-domain and out-of-domain (unseen horse) testing. We find that pretraining on ImageNet strongly improves out-of-domain performance. Moreover, we show that for both pretrained and networks trained from scratch, better ImageNet-performing architectures perform better for pose estimation, with a substantial improvement on out-of-domain data when pretrained. Collectively, our results demonstrate that transfer learning is particularly beneficial for out-of-domain robustness.

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:1909.11229/code)