# Pretraining boosts out-of-domain robustness for pose estimation

arXiv: https://arxiv.org/abs/1909.11229 · HTML: https://mlsanity.com/paper/1909.11229/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2019.

## Built on by (most cited first, 30 of 47)

- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [AP-10K: A Benchmark for Animal Pose Estimation in the Wild](https://mlsanity.com/paper/2108.12617/) (2021)
- [MagicPony: Learning Articulated 3D Animals in the Wild](https://mlsanity.com/paper/2211.12497/) (2022)
- [Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding](https://mlsanity.com/paper/2204.08129/) (2022)
- [TAPVid-3D: A Benchmark for Tracking Any Point in 3D](https://mlsanity.com/paper/2407.05921/) (2024)
- [AllTracker: Efficient Dense Point Tracking at High Resolution](https://mlsanity.com/paper/2506.07310/) (2025)
- [APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking](https://mlsanity.com/paper/2206.05683/) (2022)
- [OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association](https://mlsanity.com/paper/2103.02440/) (2021)
- [Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape](https://mlsanity.com/paper/2308.11737/) (2023)
- [SuperAnimal pretrained pose estimation models for behavioral analysis](https://mlsanity.com/paper/2203.07436/) (2022)
- [AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild](https://mlsanity.com/paper/2205.00158/) (2022)
- [Pose for Everything: Towards Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2207.10387/) (2022)
- [MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding](https://mlsanity.com/paper/2306.00576/) (2023)
- [Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation](https://mlsanity.com/paper/2106.00903/) (2021)
- [Do better ImageNet classifiers assess perceptual similarity better?](https://mlsanity.com/paper/2203.04946/) (2022)
- [AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild](https://mlsanity.com/paper/2103.13282/) (2021)
- [A Novel Dataset for Keypoint Detection of quadruped Animals from Images](https://mlsanity.com/paper/2108.13958/) (2021)
- [Improving Neural Machine Translation by Bidirectional Training](https://mlsanity.com/paper/2109.07780/) (2021)
- [AmadeusGPT: a natural language interface for interactive animal behavioral analysis](https://mlsanity.com/paper/2307.04858/) (2023)
- [Refining Pre-Trained Motion Models](https://mlsanity.com/paper/2401.00850/) (2024)
- [The USYD-JD Speech Translation System for IWSLT 2021](https://mlsanity.com/paper/2107.11572/) (2021)
- [OpenApePose: a database of annotated ape photographs for pose estimation](https://mlsanity.com/paper/2212.00741/) (2022)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond](https://mlsanity.com/paper/2312.15612/) (2023)
- [Measuring and modeling the motor system with machine learning](https://mlsanity.com/paper/2103.11775/) (2021)
- [Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images](https://mlsanity.com/paper/2410.03438/) (2024)
- [Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real Data](https://mlsanity.com/paper/2208.13944/) (2022)
- [Synthetic Data-based Detection of Zebras in Drone Imagery](https://mlsanity.com/paper/2305.00432/) (2023)
- [Animal Behavior Analysis Methods Using Deep Learning: A Survey](https://mlsanity.com/paper/2405.14002/) (2024)
- [Automated Detection of Cat Facial Landmarks](https://mlsanity.com/paper/2310.09793/) (2023)

## Abstract (arXiv)

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.