Human Pose Estimation with Iterative Error Feedback
This work addresses the challenge of modeling structured output dependencies in tasks like pose estimation, offering a novel framework that enhances hierarchical feature extractors for improved accuracy in computer vision applications.
The paper tackles the problem of articulated human pose estimation by introducing Iterative Error Feedback (IEF), a self-correcting model that uses top-down feedback to progressively refine predictions, achieving state-of-the-art performance on MPII and LSP benchmarks without requiring ground truth scale annotation.
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.