Pixel-level labelling tasks, such as semantic segmentation, play a central
role in image understanding. Recent approaches have attempted to harness the
capabilities of deep learning techniques for image recognition to tackle
pixel-level labelling tasks. One central issue in this methodology is the
limited capacity of deep learning techniques to delineate visual objects. To
solve this problem, we introduce a new form of convolutional neural network
that combines the strengths of Convolutional Neural Networks (CNNs) and
Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To
this end, we formulate mean-field approximate inference for the Conditional
Random Fields with Gaussian pairwise potentials as Recurrent Neural Networks.
This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a
deep network that has desirable properties of both CNNs and CRFs. Importantly,
our system fully integrates CRF modelling with CNNs, making it possible to
train the whole deep network end-to-end with the usual back-propagation
algorithm, avoiding offline post-processing methods for object delineation. We
apply the proposed method to the problem of semantic image segmentation,
obtaining top results on the challenging Pascal VOC 2012 segmentation
benchmark.
%0 Generic
%1 zheng2015conditional
%A Zheng, Shuai
%A Jayasumana, Sadeep
%A Romera-Paredes, Bernardino
%A Vineet, Vibhav
%A Su, Zhizhong
%A Du, Dalong
%A Huang, Chang
%A Torr, Philip H. S.
%D 2015
%K VB acreuser deeplearning
%R 10.1109/ICCV.2015.179
%T Conditional Random Fields as Recurrent Neural Networks
%U http://arxiv.org/abs/1502.03240
%X Pixel-level labelling tasks, such as semantic segmentation, play a central
role in image understanding. Recent approaches have attempted to harness the
capabilities of deep learning techniques for image recognition to tackle
pixel-level labelling tasks. One central issue in this methodology is the
limited capacity of deep learning techniques to delineate visual objects. To
solve this problem, we introduce a new form of convolutional neural network
that combines the strengths of Convolutional Neural Networks (CNNs) and
Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To
this end, we formulate mean-field approximate inference for the Conditional
Random Fields with Gaussian pairwise potentials as Recurrent Neural Networks.
This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a
deep network that has desirable properties of both CNNs and CRFs. Importantly,
our system fully integrates CRF modelling with CNNs, making it possible to
train the whole deep network end-to-end with the usual back-propagation
algorithm, avoiding offline post-processing methods for object delineation. We
apply the proposed method to the problem of semantic image segmentation,
obtaining top results on the challenging Pascal VOC 2012 segmentation
benchmark.
@misc{zheng2015conditional,
abstract = {Pixel-level labelling tasks, such as semantic segmentation, play a central
role in image understanding. Recent approaches have attempted to harness the
capabilities of deep learning techniques for image recognition to tackle
pixel-level labelling tasks. One central issue in this methodology is the
limited capacity of deep learning techniques to delineate visual objects. To
solve this problem, we introduce a new form of convolutional neural network
that combines the strengths of Convolutional Neural Networks (CNNs) and
Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To
this end, we formulate mean-field approximate inference for the Conditional
Random Fields with Gaussian pairwise potentials as Recurrent Neural Networks.
This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a
deep network that has desirable properties of both CNNs and CRFs. Importantly,
our system fully integrates CRF modelling with CNNs, making it possible to
train the whole deep network end-to-end with the usual back-propagation
algorithm, avoiding offline post-processing methods for object delineation. We
apply the proposed method to the problem of semantic image segmentation,
obtaining top results on the challenging Pascal VOC 2012 segmentation
benchmark.},
added-at = {2016-04-15T07:04:00.000+0200},
author = {Zheng, Shuai and Jayasumana, Sadeep and Romera-Paredes, Bernardino and Vineet, Vibhav and Su, Zhizhong and Du, Dalong and Huang, Chang and Torr, Philip H. S.},
biburl = {https://www.bibsonomy.org/bibtex/209eda78ca8175fafcfe007d20cc0ca77/pixor},
description = {1502.03240v3.pdf},
doi = {10.1109/ICCV.2015.179},
interhash = {0005887723a4b8a07c67a94ea7a56104},
intrahash = {09eda78ca8175fafcfe007d20cc0ca77},
keywords = {VB acreuser deeplearning},
note = {cite arxiv:1502.03240v3.pdfComment: This paper is published in IEEE ICCV 2015},
timestamp = {2016-04-15T07:04:00.000+0200},
title = {Conditional Random Fields as Recurrent Neural Networks},
url = {http://arxiv.org/abs/1502.03240},
year = 2015
}