Efficient Object Localization Using Convolutional Networks

TL;DR

This paper presents a new convolutional network architecture with a position refinement model that enhances human joint localization accuracy, approaching human annotation variance and outperforming existing methods.

Contribution

Introduces a novel cascade architecture combining a ConvNet with a position refinement model for improved localization accuracy.

Findings

Variance of the detector approaches human annotation variance.

Outperforms all existing methods on MPII-human-pose dataset.

Achieves state-of-the-art accuracy on human joint localization.

Abstract

Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling and sub-sampling layers which reduce computational requirements, introduce invariance and prevent over-training. These benefits of pooling come at the cost of reduced localization accuracy. We introduce a novel architecture which includes an efficient `position refinement' model that is trained to estimate the joint offset location within a small region of the image. This refinement model is jointly trained in cascade with a state-of-the-art ConvNet model to achieve improved accuracy in human joint location estimation. We show that the variance of our detector approaches the variance of human annotations on the FLIC dataset and outperforms all existing approaches on the MPII-human-pose dataset.