Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

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

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 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, 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.
Fichier principal
Vignette du fichier
rtf.pdf (4.86 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01410872 , version 1 (06-12-2016)

Identifiers

Cite

Siddhartha Chandra, Iasonas Kokkinos. Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs. European Conference on Computer Vision, Sep 2016, Amsterdam, Netherlands. ⟨10.1007/978-3-319-46478-7_25⟩. ⟨hal-01410872⟩
317 View
242 Download

Altmetric

Share

Gmail Facebook X LinkedIn More