# Adversarial Semantic Data Augmentation for Human Pose Estimation

arXiv: https://arxiv.org/abs/2008.00697 · HTML: https://mlsanity.com/paper/2008.00697/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 22 of 22)

- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (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)
- [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Intra-Source Style Augmentation for Improved Domain Generalization](https://mlsanity.com/paper/2210.10175/) (2022)
- [PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation](https://mlsanity.com/paper/2208.07755/) (2022)
- [Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module](https://mlsanity.com/paper/2303.04346/) (2023)
- [ProbPose: A Probabilistic Approach to 2D Human Pose Estimation](https://mlsanity.com/paper/2412.02254/) (2024)
- [LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering](https://mlsanity.com/paper/2108.00351/) (2021)
- [Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization](https://mlsanity.com/paper/2307.00648/) (2023)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Probabilistic Regression with Huber Distributions](https://mlsanity.com/paper/2111.10296/) (2021)
- [Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data](https://mlsanity.com/paper/2307.06737/) (2023)
- [Data Augmentation in Human-Centric Vision](https://mlsanity.com/paper/2403.08650/) (2024)
- [Recovering Complete Actions for Cross-dataset Skeleton Action Recognition](https://mlsanity.com/paper/2410.23641/) (2024)
- [Location-free Human Pose Estimation](https://mlsanity.com/paper/2205.12619/) (2022)
- [PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data](https://mlsanity.com/paper/2503.13025/) (2025)
- [Improving Pose Estimation through Contextual Activity Fusion](https://mlsanity.com/paper/2111.02500/) (2021)
- [Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them](https://mlsanity.com/paper/2401.11723/) (2024)

## Abstract (arXiv)

Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and nearby person. To enlarge the amounts of challenging cases, previous methods augmented images by cropping and pasting image patches with weak semantics, which leads to unrealistic appearance and limited diversity. We instead propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. Furthermore, we propose Adversarial Semantic Data Augmentation (ASDA), which exploits a generative network to dynamiclly predict tailored pasting configuration. Given off-the-shelf pose estimation network as discriminator, the generator seeks the most confusing transformation to increase the loss of the discriminator while the discriminator takes the generated sample as input and learns from it. The whole pipeline is optimized in an adversarial manner. State-of-the-art results are achieved on challenging benchmarks.