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

TitleAffinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding
Publication TypeConference Paper
Year of Publication2016
AuthorsMaire, M., Narihira T., & Yu S. X.
Published inProceedings of IEEE Conference on Computer Vision and Pattern Recognition
Date Published06/2016
PublisherIEEE
Keywordsaffinity CNN, angular embedding, figure-ground organization, image segmentation, object segmentation, spectral embedding
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.

URLhttp://www1.icsi.berkeley.edu/~stellayu/publication/doc/2016affinityCVPR.pdf
ICSI Research Group

Vision