A CNN Cascade for Landmark Guided Semantic Part Segmentation

TL;DR

This paper introduces a CNN cascade that leverages pose-specific landmarks to improve semantic part segmentation, demonstrating significant performance gains in facial segmentation tasks.

Contribution

It is the first to explore the interplay between pose estimation and semantic segmentation using a CNN cascade architecture.

Findings

Large performance improvement on face datasets

Effective use of landmarks to guide segmentation

First integration of pose estimation with segmentation in CNNs

Abstract

This paper proposes a CNN cascade for semantic part segmentation guided by pose-specific information encoded in terms of a set of landmarks (or keypoints). There is large amount of prior work on each of these tasks separately, yet, to the best of our knowledge, this is the first time in literature that the interplay between pose estimation and semantic part segmentation is investigated. To address this limitation of prior work, in this paper, we propose a CNN cascade of tasks that firstly performs landmark localisation and then uses this information as input for guiding semantic part segmentation. We applied our architecture to the problem of facial part segmentation and report large performance improvement over the standard unguided network on the most challenging face datasets. Testing code and models will be published online at http://cs.nott.ac.uk/~psxasj/.