Conditional Random Fields as Recurrent Neural Networks
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.
Code (6)
Tasks
Image SegmentationReal-Time Semantic SegmentationSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MVSCRF: Learning Multi-View Stereo With Conditional Random Fields
We present a deep-learning architecture for multi-view stereo with conditional random fields (MVSCRF). Given an arbitrary number of input images, we first use a U-shape neural network to extract deep features incorporati…
End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks
Recent years have seen a sharp increase in the number of related yet distinct advances in semantic segmentation. Here, we tackle this problem by leveraging the respective strengths of these advances. That is, we formulat…
SegmentationSemantic SegmentationImproving the Morphological Analysis of Classical Sanskrit
The paper describes a new tagset for the morphological disambiguation of Sanskrit, and compares the accuracy of two machine learning methods (Conditional Random Fields, deep recurrent neural networks) for this task, with…
BIG-bench Machine LearningLemmatizationMorphological AnalysisMorphological DisambiguationOpinion Dynamics Modeling for Movie Review Transcripts Classification with Hidden Conditional Random Fields
In this paper, the main goal is to detect a movie reviewer's opinion using hidden conditional random fields. This model allows us to capture the dynamics of the reviewer's opinion in the transcripts of long unsegmented a…
General ClassificationConditional Random Fields as Recurrent Neural Networks for 3D Medical Imaging Segmentation
The Conditional Random Field as a Recurrent Neural Network layer is a recently proposed algorithm meant to be placed on top of an existing Fully-Convolutional Neural Network to improve the quality of semantic segmentatio…
3D Medical Imaging SegmentationMedical Image SegmentationSegmentationSemantic Segmentation+1