# VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

arXiv: https://arxiv.org/abs/2210.06028 · HTML: https://mlsanity.com/paper/2210.06028/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 59 references that are in the map.
- First posted on arXiv 12 Oct 2022.

## Builds on (most cited first, 30 of 33)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation](https://mlsanity.com/paper/1406.2984/) (2014)
- [PifPaf: Composite Fields for Human Pose Estimation](https://mlsanity.com/paper/1903.06593/) (2019)
- [Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows](https://mlsanity.com/paper/2107.13788/) (2021)
- [Sequential Graph Convolutional Network for Active Learning](https://mlsanity.com/paper/2006.10219/) (2020)
- [OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association](https://mlsanity.com/paper/2103.02440/) (2021)
- [PoseFix: Model-agnostic General Human Pose Refinement Network](https://mlsanity.com/paper/1812.03595/) (2018)
- [Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild](https://mlsanity.com/paper/2103.10978/) (2021)
- [MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation](https://mlsanity.com/paper/1906.06059/) (2019)
- [Structured Uncertainty Prediction Networks](https://mlsanity.com/paper/1802.07079/) (2018)
- [Regressive Domain Adaptation for Unsupervised Keypoint Detection](https://mlsanity.com/paper/2103.06175/) (2021)
- [Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement](https://mlsanity.com/paper/2007.10599/) (2020)
- [Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species](https://mlsanity.com/paper/2112.06183/) (2021)
- [Active Learning for Speech Recognition: the Power of Gradients](https://mlsanity.com/paper/1612.03226/) (2016)
- [Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2203.15293/) (2022)
- [Toward fast and accurate human pose estimation via soft-gated skip connections](https://mlsanity.com/paper/2002.11098/) (2020)
- [Active Learning for Bayesian 3D Hand Pose Estimation](https://mlsanity.com/paper/2010.00694/) (2020)
- [Learning Human Pose Estimation Features with Convolutional Networks](https://mlsanity.com/paper/1312.7302/) (2013)
- [Keypoint Communities](https://mlsanity.com/paper/2110.00988/) (2021)
- [BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty](https://mlsanity.com/paper/2007.06096/) (2020)

## Built on by (most cited first, 9 of 9)

- [Neural Interactive Keypoint Detection](https://mlsanity.com/paper/2308.10174/) (2023)
- [Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment](https://mlsanity.com/paper/2503.17267/) (2025)
- [A Unified Approach Towards Active Learning and Out-of-Distribution Detection](https://mlsanity.com/paper/2405.11337/) (2024)
- [TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression](https://mlsanity.com/paper/2310.18953/) (2023)
- [Active Transfer Learning for Efficient Video-Specific Human Pose Estimation](https://mlsanity.com/paper/2311.05041/) (2023)
- [Can Pose Transfer Models Generate Realistic Human Motion?](https://mlsanity.com/paper/2501.15648/) (2025)
- [Attend-and-Refine: Interactive keypoint estimation and quantitative cervical vertebrae analysis for bone age assessment](https://mlsanity.com/paper/2507.07670/) (2025)
- [Personalized Pose Forecasting](https://mlsanity.com/paper/2312.03528/) (2023)
- [IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1](https://mlsanity.com/paper/2603.19625/) (2026)

## Abstract (arXiv)

Advances in computing have enabled widespread access to pose estimation, creating new sources of data streams. Unlike mock set-ups for data collection, tapping into these data streams through on-device active learning allows us to directly sample from the real world to improve the spread of the training distribution. However, on-device computing power is limited, implying that any candidate active learning algorithm should have a low compute footprint while also being reliable. Although multiple algorithms cater to pose estimation, they either use extensive compute to power state-of-the-art results or are not competitive in low-resource settings. We address this limitation with VL4Pose (Visual Likelihood For Pose Estimation), a first principles approach for active learning through out-of-distribution detection. We begin with a simple premise: pose estimators often predict incoherent poses for out-of-distribution samples. Hence, can we identify a distribution of poses the model has been trained on, to identify incoherent poses the model is unsure of? Our solution involves modelling the pose through a simple parametric Bayesian network trained via maximum likelihood estimation. Therefore, poses incurring a low likelihood within our framework are out-of-distribution samples making them suitable candidates for annotation. We also observe two useful side-outcomes: VL4Pose in-principle yields better uncertainty estimates by unifying joint and pose level ambiguity, as well as the unintentional but welcome ability of VL4Pose to perform pose refinement in limited scenarios. We perform qualitative and quantitative experiments on three datasets: MPII, LSP and ICVL, spanning human and hand pose estimation. Finally, we note that VL4Pose is simple, computationally inexpensive and competitive, making it suitable for challenging tasks such as on-device active learning.