Learning affinity via spatial propagation networks

Sifei Liu, Shalini De Mello, Jinwei Gu, Guangyu Zhong, Ming Hsuan Yang, Jan Kautz

Research output: Contribution to journalConference article

40 Citations (Scopus)

Abstract

In this paper, we propose spatial propagation networks for learning the affinity matrix for vision tasks. We show that by constructing a row/column linear propagation model, the spatially varying transformation matrix exactly constitutes an affinity matrix that models dense, global pairwise relationships of an image. Specifically, we develop a three-way connection for the linear propagation model, which (a) formulates a sparse transformation matrix, where all elements can be outputs from a deep CNN, but (b) results in a dense affinity matrix that effectively models any task-specific pairwise similarity matrix. Instead of designing the similarity kernels according to image features of two points, we can directly output all the similarities in a purely data-driven manner. The spatial propagation network is a generic framework that can be applied to many affinity-related tasks, such as image matting, segmentation and colorization, to name a few. Essentially, the model can learn semantically-aware affinity values for high-level vision tasks due to the powerful learning capability of deep CNNs. We validate the framework on the task of refinement of image segmentation boundaries. Experiments on the HELEN face parsing and PASCAL VOC-2012 semantic segmentation tasks show that the spatial propagation network provides a general, effective and efficient solution for generating high-quality segmentation results.

Original languageEnglish
Pages (from-to)1521-1531
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2017-December
Publication statusPublished - 2017 Jan 1
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: 2017 Dec 42017 Dec 9

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint Dive into the research topics of 'Learning affinity via spatial propagation networks'. Together they form a unique fingerprint.

  • Cite this

    Liu, S., De Mello, S., Gu, J., Zhong, G., Yang, M. H., & Kautz, J. (2017). Learning affinity via spatial propagation networks. Advances in Neural Information Processing Systems, 2017-December, 1521-1531.