Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding

Michael Maire, Takuya Narihira, Stella X. Yu; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 174-182

Abstract


Spectral embedding provides a framework for solving perceptual organization problems, including image segmentation and figure/ground organization. From an affinity matrix describing pairwise relationships between pixels, it clusters pixels into regions, and, using a complex-valued extension, orders pixels according to layer. We train a convolutional neural network (CNN) to directly predict the pairwise relationships that define this affinity matrix. Spectral embedding then resolves these predictions into a globally-consistent segmentation and figure/ground organization of the scene. Experiments demonstrate significant benefit to this direct coupling compared to prior works which use explicit intermediate stages, such as edge detection, on the pathway from image to affinities. Our results suggest spectral embedding as a powerful alternative to the conditional random field (CRF)-based globalization schemes typically coupled to deep neural networks.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Maire_2016_CVPR,
author = {Maire, Michael and Narihira, Takuya and Yu, Stella X.},
title = {Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}