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

Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs

Chandra, S; Kokkinos, I; (2016) Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs. In: Leibe, B and Matas, J and Sebe, N and Welling, M, (eds.) Computer Vision – ECCV 2016. (pp. pp. 402-418). Springer: Cham, Switzerland. Green open access

[thumbnail of Kokkino_arxiv_sid.pdf]
Preview
Text
Kokkino_arxiv_sid.pdf - Accepted Version

Download (5MB) | Preview

Abstract

In this work we propose a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields (G-CRF) with Deep Learning: (a) our structured prediction task has a unique global optimum that is obtained exactly from the solution of a linear system (b) the gradients of our model parameters are analytically computed using closed form expressions, in contrast to the memory-demanding contemporary deep structured prediction approaches [1, 2] that rely on back-propagation-through-time, (c) our pairwise terms do not have to be simple hand-crafted expressions, as in the line of works building on the DenseCRF [1, 3], but can rather be ‘discovered’ from data through deep architectures, and (d) out system can trained in an end-to-end manner. Building on standard tools from numerical analysis we develop very efficient algorithms for inference and learning, as well as a customized technique adapted to the semantic segmentation task. This efficiency allows us to explore more sophisticated architectures for structured prediction in deep learning: we introduce multi-resolution architectures to couple information across scales in a joint optimization framework, yielding systematic improvements. We demonstrate the utility of our approach on the challenging VOC PASCAL 2012 image segmentation benchmark, showing substantial improvements over strong baselines. We make all of our code and experiments available at https://github.com/siddharthachandra/gcrf.

Type: Proceedings paper
Title: Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
Event: Computer Vision – ECCV 2016
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-319-46478-7_25
Publisher version: https://doi.org/10.1007/978-3-319-46478-7_25
Language: English
Additional information: Copyright © Springer International Publishing AG 2016. This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
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/1527530
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item