Human Pose Estimation with Iterative Error Feedback

Citations Over TimeTop 1% of 2016 papers

Abstract

Hierarchical feature extractors such as Convolutional Networks (ConvNets) have achieved impressive performance on a variety of classification tasks using purely feedforward processing. Feedforward architectures can learn rich representations of the input space but do not explicitly model dependencies in the output spaces, that are quite structured for tasks such as articulated human pose estimation or object segmentation. Here we propose a framework that expands the expressive power of hierarchical feature extractors to encompass both input and output spaces, by introducing top-down feedback. Instead of directly predicting the outputs in one go, we use a self-correcting model that progressively changes an initial solution by feeding back error predictions, in a process we call Iterative Error Feedback (IEF). IEF shows excellent performance on the task of articulated pose estimation in the challenging MPII and LSP benchmarks, matching the state-of-the-art without requiring ground truth scale annotation.

Related Papers

• → 2D Human Pose Estimation: New Benchmark and State of the Art Analysis(2014)2,765 cited
• → Very Deep Convolutional Networks for Large-Scale Image Recognition(2014)75,407 cited
• → Stacked Hourglass Networks for Human Pose Estimation(2016)536 cited
• → Joint Training of a Convolutional Network and a Graphical Model for\n Human Pose Estimation(2014)472 cited
• Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations(2014)