Learning Affinity via Spatial Propagation Networks

TL;DR

This paper introduces spatial propagation networks that learn dense, global affinity matrices for vision tasks, enabling improved image segmentation and boundary refinement through a data-driven, deep learning approach.

Contribution

The paper presents a novel framework for learning affinity matrices directly from data using deep neural networks, applicable to various vision tasks.

Findings

Improved segmentation boundary refinement on benchmark datasets.

Effective modeling of dense, global pairwise relationships.

Versatile application to multiple vision tasks.

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 the output 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, including but not limited to 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 the deep neural network classifier. We validate the framework on the task of refinement for 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.