A CNN cascade for landmark guided semantic part segmentation

Jackson, Aaron S.; Valstar, Michel; Tzimiropoulos, Georgios

Abstract

This paper proposes a CNN cascade for semantic part segmentation guided by pose-specifc 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/.

Citation

Jackson, A. S., Valstar, M., & Tzimiropoulos, G. (2016). A CNN cascade for landmark guided semantic part segmentation.

• Conference Name: ECCV 2016 Workshop, Geometry meets Deep Learning
• Acceptance Date: Sep 3, 2016
• Publication Date: Oct 7, 2016
• Deposit Date: Sep 29, 2016
• Publicly Available Date: Oct 7, 2016
• Peer Reviewed: Peer Reviewed
• Keywords: pose estimation, landmark localisation, semantic part seg-; mentation, faces
• Public URL: https://nottingham-repository.worktribe.com/output/824205
• Related Public URLs: http://www.eccv2016.org/; https://sites.google.com/site/deepgeometry/
• Additional Information: Published in: Proceedings of 14th European Conference on Computer Vision 2016, Workshop, Geometry meets Deep Learning.; Lecture notes in computer science. Springer.; ; The final publication is available at link.springer.com.