UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Dense and Low-Rank Gaussian CRFs Using Deep Embeddings

Chandra, S; Usunier, N; Kokkinos, I; (2017) Dense and Low-Rank Gaussian CRFs Using Deep Embeddings. In: (Proceedings) 16th IEEE International Conference on Computer Vision (ICCV). (pp. pp. 5113-5122). IEEE Green open access

[thumbnail of Chandra_Dense_and_Low-Rank_ICCV_2017_paper.pdf]
Preview
Text
Chandra_Dense_and_Low-Rank_ICCV_2017_paper.pdf - Published Version

Download (2MB) | Preview

Abstract

In this work we introduce a structured prediction model that endows the Deep Gaussian Conditional Random Field (G-CRF) with a densely connected graph structure. We keep memory and computational complexity under control by expressing the pairwise interactions as inner products of low-dimensional, learnable embeddings. The G-CRF system matrix is therefore low-rank, allowing us to solve the resulting system in a few milliseconds on the GPU by using conjugate gradient. As in G-CRF, inference is exact, the unary and pairwise terms are jointly trained end-to-end by using analytic expressions for the gradients, while we also develop even faster, Potts-type variants of our embeddings. We show that the learned embeddings capture pixel-to-pixel affinities in a task-specific manner, while our approach achieves state of the art results on three challenging benchmarks, namely semantic segmentation, human part segmentation, and saliency estimation. Our implementation is fully GPU based, built on top of the Caffe library, and is available at https://github.com/siddharthachandra/gcrf-v2.0.

Type: Proceedings paper
Title: Dense and Low-Rank Gaussian CRFs Using Deep Embeddings
Event: 16th IEEE International Conference on Computer Vision (ICCV)
Location: Venice, ITALY
Dates: 22 October 2017 - 29 October 2017
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICCV.2017.546
Publisher version: https://doi.org/10.1109/ICCV.2017.546
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Science & Technology, Technology, Computer Science, Artificial Intelligence, Engineering, Electrical & Electronic, Computer Science, Engineering
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10060978
Downloads since deposit
72Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item