Conditional random fields as recurrent neural networks
S Zheng, S Jayasumana… - Proceedings of the …, 2015 - cv-foundation.org
Proceedings of the IEEE international conference on computer vision, 2015•cv-foundation.org
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 …
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 …
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.
cv-foundation.org