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 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.

DOI: 10.1109/ICCV.2015.179

Extracted Key Phrases

6 Figures and Tables

Citations per Year

617 Citations

Semantic Scholar estimates that this publication has 617 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Zheng2015ConditionalRF, title={Conditional Random Fields as Recurrent Neural Networks}, author={Shuai Zheng and Sadeep Jayasumana and Bernardino Romera-Paredes and Vibhav Vineet and Zhizhong Su and Dalong Du and Chang Huang and Philip H. S. Torr}, journal={2015 IEEE International Conference on Computer Vision (ICCV)}, year={2015}, pages={1529-1537} }