# Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization

arXiv: https://arxiv.org/abs/2201.08613 · HTML: https://mlsanity.com/paper/2201.08613/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 79 references that are in the map.
- First posted on arXiv 21 Jan 2022.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [Designing Neural Network Architectures using Reinforcement Learning](https://mlsanity.com/paper/1611.02167/) (2016)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Learning to Estimate 3D Hand Pose from Single RGB Images](https://mlsanity.com/paper/1705.01389/) (2017)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [Teacher-Student Curriculum Learning](https://mlsanity.com/paper/1707.00183/) (2017)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [Whole-Body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2007.11858/) (2020)
- [Distribution-Aware Coordinate Representation for Human Pose Estimation](https://mlsanity.com/paper/1910.06278/) (2019)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Data Distillation: Towards Omni-Supervised Learning](https://mlsanity.com/paper/1712.04440/) (2017)
- [Unsupervised Learning of Object Landmarks through Conditional Image Generation](https://mlsanity.com/paper/1806.07823/) (2018)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)

## Built on by (most cited first, 14 of 14)

- [LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency](https://mlsanity.com/paper/2404.12872/) (2024)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [Dynamic Curriculum Learning for Great Ape Detection in the Wild](https://mlsanity.com/paper/2205.00275/) (2022)
- [Progressive Transformation Learning for Leveraging Virtual Images in Training](https://mlsanity.com/paper/2211.01778/) (2022)
- [You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception](https://mlsanity.com/paper/2312.05525/) (2023)
- [OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection](https://mlsanity.com/paper/2409.19899/) (2024)
- [Few-shot Geometry-Aware Keypoint Localization](https://mlsanity.com/paper/2303.17216/) (2023)
- [Unsupervised Domain Adaptation for Anatomical Landmark Detection](https://mlsanity.com/paper/2308.13286/) (2023)
- [Rethinking Self-training for Semi-supervised Landmark Detection: A Selection-free Approach](https://mlsanity.com/paper/2404.04556/) (2024)
- [SDTracker: Synthetic Data Based Multi-Object Tracking](https://mlsanity.com/paper/2303.14653/) (2023)
- [Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation](https://mlsanity.com/paper/2310.00099/) (2023)
- [Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training](https://mlsanity.com/paper/2402.11566/) (2024)
- [Incremental Object Keypoint Learning](https://mlsanity.com/paper/2503.20248/) (2025)
- [GKDT: General Keypoint Detection Transformer](https://mlsanity.com/paper/2607.00752/) (2026)

## Abstract (arXiv)

Localizing keypoints of an object is a basic visual problem. However, supervised learning of a keypoint localization network often requires a large amount of data, which is expensive and time-consuming to obtain. To remedy this, there is an ever-growing interest in semi-supervised learning (SSL), which leverages a small set of labeled data along with a large set of unlabeled data. Among these SSL approaches, pseudo-labeling (PL) is one of the most popular. PL approaches apply pseudo-labels to unlabeled data, and then train the model with a combination of the labeled and pseudo-labeled data iteratively. The key to the success of PL is the selection of high-quality pseudo-labeled samples. Previous works mostly select training samples by manually setting a single confidence threshold. We propose to automatically select reliable pseudo-labeled samples with a series of dynamic thresholds, which constitutes a learning curriculum. Extensive experiments on six keypoint localization benchmark datasets demonstrate that the proposed approach significantly outperforms the previous state-of-the-art SSL approaches.