Learning Affinity via Spatial Propagation Networks

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.

A long version of NIPS 2017

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Grid Long Short-Term Memory
• Fully Connected Deep Structured Networks
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
• Convolutional Random Walk Networks for Semantic Image Segmentation