# Self Adversarial Training for Human Pose Estimation

arXiv: https://arxiv.org/abs/1707.02439 · HTML: https://mlsanity.com/paper/1707.02439/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2017.

## Built on by (most cited first, 8 of 8)

- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Animal Behavior Analysis Methods Using Deep Learning: A Survey](https://mlsanity.com/paper/2405.14002/) (2024)
- [Location-free Human Pose Estimation](https://mlsanity.com/paper/2205.12619/) (2022)
- [Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation](https://mlsanity.com/paper/2110.10734/) (2021)
- [Performance of different machine learning methods on activity recognition and pose estimation datasets](https://mlsanity.com/paper/2210.10247/) (2022)
- [SHARE: Single-view Human Adversarial REconstruction](https://mlsanity.com/paper/2401.00343/) (2023)
- [Refinement Module based on Parse Graph for Human Pose Estimation](https://mlsanity.com/paper/2501.11069/) (2025)

## Abstract (arXiv)

This paper presents a deep learning based approach to the problem of human pose estimation. We employ generative adversarial networks as our learning paradigm in which we set up two stacked hourglass networks with the same architecture, one as the generator and the other as the discriminator. The generator is used as a human pose estimator after the training is done. The discriminator distinguishes ground-truth heatmaps from generated ones, and back-propagates the adversarial loss to the generator. This process enables the generator to learn plausible human body configurations and is shown to be useful for improving the prediction accuracy.