# Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation

arXiv: https://arxiv.org/abs/1805.09707 · HTML: https://mlsanity.com/paper/1805.09707/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2018.

## Built on by (most cited first, 30 of 44)

- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [LAS-AT: Adversarial Training with Learnable Attack Strategy](https://mlsanity.com/paper/2203.06616/) (2022)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [Uncertainty-guided Model Generalization to Unseen Domains](https://mlsanity.com/paper/2103.07531/) (2021)
- [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021)
- [TeachAugment: Data Augmentation Optimization Using Teacher Knowledge](https://mlsanity.com/paper/2202.12513/) (2022)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [On Implicit Bias in Overparameterized Bilevel Optimization](https://mlsanity.com/paper/2212.14032/) (2022)
- [A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects](https://mlsanity.com/paper/2305.07348/) (2023)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach](https://mlsanity.com/paper/2108.02888/) (2021)
- [Intra-Source Style Augmentation for Improved Domain Generalization](https://mlsanity.com/paper/2210.10175/) (2022)
- [Free-form tumor synthesis in computed tomography images via richer generative adversarial network](https://mlsanity.com/paper/2104.09701/) (2021)
- [PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation](https://mlsanity.com/paper/2208.07755/) (2022)
- [Are Data-driven Explanations Robust against Out-of-distribution Data?](https://mlsanity.com/paper/2303.16390/) (2023)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks](https://mlsanity.com/paper/2206.06544/) (2022)
- [Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation](https://mlsanity.com/paper/2208.00090/) (2022)
- [An Adversarial Human Pose Estimation Network Injected with Graph Structure](https://mlsanity.com/paper/2103.15534/) (2021)
- [The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition](https://mlsanity.com/paper/2105.13061/) (2021)
- [DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimation](https://mlsanity.com/paper/2207.09303/) (2022)
- [Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization](https://mlsanity.com/paper/2307.00648/) (2023)
- [BdSL36: A Dataset for Bangladeshi Sign Letters Recognition](https://mlsanity.com/paper/2110.00869/) (2021)
- [Deep Iterative 2D/3D Registration](https://mlsanity.com/paper/2107.10004/) (2021)
- [Semantic Perturbations with Normalizing Flows for Improved Generalization](https://mlsanity.com/paper/2108.07958/) (2021)
- [3D Human Pose Estimation Using M"obius Graph Convolutional Networks](https://mlsanity.com/paper/2203.10554/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [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)

## Abstract (arXiv)

Random data augmentation is a critical technique to avoid overfitting in training deep neural network models. However, data augmentation and network training are usually treated as two isolated processes, limiting the effectiveness of network training. Why not jointly optimize the two? We propose adversarial data augmentation to address this limitation. The main idea is to design an augmentation network (generator) that competes against a target network (discriminator) by generating `hard' augmentation operations online. The augmentation network explores the weaknesses of the target network, while the latter learns from `hard' augmentations to achieve better performance. We also design a reward/penalty strategy for effective joint training. We demonstrate our approach on the problem of human pose estimation and carry out a comprehensive experimental analysis, showing that our method can significantly improve state-of-the-art models without additional data efforts.