Active Learning with Pseudo-Labels for Multi-View 3D Pose Estimation

by   Qi Feng, et al.

Pose estimation of the human body/hand is a fundamental problem in computer vision, and learning-based solutions require a large amount of annotated data. Given limited annotation budgets, a common approach to increasing label efficiency is Active Learning (AL), which selects examples with the highest value to annotate, but choosing the selection strategy is often nontrivial. In this work, we improve Active Learning for the problem of 3D pose estimation in a multi-view setting, which is of increasing importance in many application scenarios. We develop a framework that allows us to efficiently extend existing single-view AL strategies, and then propose two novel AL strategies that make full use of multi-view geometry. Moreover, we demonstrate additional performance gains by incorporating predicted pseudo-labels, which is a form of self-training. Our system significantly outperforms baselines in 3D body and hand pose estimation on two large-scale benchmarks: CMU Panoptic Studio and InterHand2.6M. Notably, on CMU Panoptic Studio, we are able to match the performance of a fully-supervised model using only 20 data.



page 2

page 4

page 8

page 12


Learning Temporal 3D Human Pose Estimation with Pseudo-Labels

We present a simple, yet effective, approach for self-supervised 3D huma...

MVHM: A Large-Scale Multi-View Hand Mesh Benchmark for Accurate 3D Hand Pose Estimation

Estimating 3D hand poses from a single RGB image is challenging because ...

Active Learning for Bayesian 3D Hand Pose Estimation

We propose a Bayesian approximation to a deep learning architecture for ...

Active Learning++: Incorporating Annotator's Rationale using Local Model Explanation

We propose a new active learning (AL) framework, Active Learning++, whic...

Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation

Timely detection of horse pain is important for equine welfare. Horses e...

Multi-View Video-Based 3D Hand Pose Estimation

Hand pose estimation (HPE) can be used for a variety of human-computer i...

On Using Active Learning and Self-Training when Mining Performance Discussions on Stack Overflow

Abundant data is the key to successful machine learning. However, superv...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.