scispace - formally typeset
Search or ask a question
Topic

Conditional random field

About: Conditional random field is a research topic. Over the lifetime, 5500 publications have been published within this topic receiving 197014 citations. The topic is also known as: CRF.


Papers
More filters
Proceedings ArticleDOI
07 Dec 2015
TL;DR: In this article, 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 is introduced.
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 Conditional Random Fields with Gaussian pairwise potentials and mean-field approximate inference 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.

1,973 citations

Proceedings ArticleDOI
TL;DR: 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 is introduced, and top results are obtained on the challenging Pascal VOC 2012 segmentation benchmark.
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.

1,873 citations

Book ChapterDOI
Léon Bottou1
01 Jan 2012
TL;DR: This chapter provides background material, explains why SGD is a good learning algorithm when the training set is large, and provides useful recommendations.
Abstract: Chapter 1 strongly advocates the stochastic back-propagation method to train neural networks. This is in fact an instance of a more general technique called stochastic gradient descent (SGD). This chapter provides background material, explains why SGD is a good learning algorithm when the training set is large, and provides useful recommendations.

1,666 citations

Proceedings ArticleDOI
27 May 2003
TL;DR: This work shows how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model.
Abstract: Conditional random fields for sequence labeling offer advantages over both generative models like HMMs and classifiers applied at each sequence position. Among sequence labeling tasks in language processing, shallow parsing has received much attention, with the development of standard evaluation datasets and extensive comparison among methods. We show here how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model. Improved training methods based on modern optimization algorithms were critical in achieving these results. We present extensive comparisons between models and training methods that confirm and strengthen previous results on shallow parsing and training methods for maximum-entropy models.

1,472 citations

Book ChapterDOI
07 May 2006
TL;DR: A new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently, is proposed, which is used for automatic visual recognition and semantic segmentation of photographs.
Abstract: This paper proposes a new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently. The learned model is used for automatic visual recognition and semantic segmentation of photographs. Our discriminative model exploits novel features, based on textons, which jointly model shape and texture. Unary classification and feature selection is achieved using shared boosting to give an efficient classifier which can be applied to a large number of classes. Accurate image segmentation is achieved by incorporating these classifiers in a conditional random field. Efficient training of the model on very large datasets is achieved by exploiting both random feature selection and piecewise training methods. High classification and segmentation accuracy are demonstrated on three different databases: i) our own 21-object class database of photographs of real objects viewed under general lighting conditions, poses and viewpoints, ii) the 7-class Corel subset and iii) the 7-class Sowerby database used in [1]. The proposed algorithm gives competitive results both for highly textured (e.g. grass, trees), highly structured (e.g. cars, faces, bikes, aeroplanes) and articulated objects (e.g. body, cow).

1,343 citations


Network Information
Related Topics (5)
Deep learning
79.8K papers, 2.1M citations
91% related
Convolutional neural network
74.7K papers, 2M citations
90% related
Feature extraction
111.8K papers, 2.1M citations
89% related
Support vector machine
73.6K papers, 1.7M citations
87% related
Object detection
46.1K papers, 1.3M citations
87% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023139
2022401
2021247
2020386
2019442
2018453