Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network

Abstract

We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network. In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part detector in a deep network architecture. We show that including the body-part detection task helps to regularize the network, directing it to converge to a good solution. We report competitive and state-of-art results on several data sets. We also empirically show that the learned neurons in the middle layer of our network are tuned to localized body parts.

References in corpus (1)

• Improving neural networks by preventing co-adaptation of feature detectors

Cited by in corpus (7)

• DeepSkeleton: Skeleton Map for 3D Human Pose Regression
• Learning Boost by Exploiting the Auxiliary Task in Multi-task Domain
• Distill-2MD-MTL: Data Distillation based on Multi-Dataset Multi-Domain Multi-Task Frame Work to Solve Face Related Tasksks, Multi Task Learning, Semi-Supervised Learning
• Multi-task Learning by Leveraging the Semantic Information
• HF-UNet: Learning Hierarchically Inter-Task Relevance in Multi-Task U-Net for Accurate Prostate Segmentation
• W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network
• Reduced Rank Multivariate Kernel Ridge Regression