Human Pose Estimation with Iterative Error Feedback

TL;DR

This paper introduces Iterative Error Feedback, a self-correcting framework that enhances hierarchical feature extractors with top-down feedback to improve structured output tasks like human pose estimation.

Contribution

It proposes a novel iterative feedback mechanism that explicitly models output dependencies, improving pose estimation without needing ground truth scale annotations.

Findings

Achieves state-of-the-art results on MPII and LSP benchmarks.

Does not require ground truth scale annotations.

Demonstrates the effectiveness of top-down feedback in structured prediction.

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.