Simulating CRF with CNN for CNN

05/06/2019
by   Lena Gorelick, et al.
0

Combining CNN with CRF for modeling dependencies between pixel labels is a popular research direction. This task is far from trivial, especially if end-to-end training is desired. In this paper, we propose a novel simple approach to CNN+CRF combination. In particular, we propose to simulate a CRF regularizer with a trainable module that has standard CNN architecture. We call this module a CRF Simulator. We can automatically generate an unlimited amount of ground truth for training such CRF Simulator without any user interaction, provided we have an efficient algorithm for optimization of the actual CRF regularizer. After our CRF Simulator is trained, it can be directly incorporated as part of any larger CNN architecture, enabling a seamless end-to-end training. In particular, the other modules can learn parameters that are more attuned to the performance of the CRF Simulator module. We demonstrate the effectiveness of our approach on the task of salient object segmentation regularized with the standard binary CRF energy. In contrast to previous work we do not need to develop and implement the complex mechanics of optimizing a specific CRF as part of CNN. In fact, our approach can be easily extended to other CRF energies, including multi-label. To the best of our knowledge we are the first to study the question of whether the output of CNNs can have regularization properties of CRFs.

READ FULL TEXT

page 6

page 7

page 9

page 11

page 14

research
11/08/2018

An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images

Fully-connected Conditional Random Field (CRF) is often used as post-pro...
research
11/30/2016

End-to-End Training of Hybrid CNN-CRF Models for Stereo

We propose a novel and principled hybrid CNN+CRF model for stereo estima...
research
12/23/2018

End-to-end Learning for Graph Decomposition

We propose a novel end-to-end trainable framework for the graph decompos...
research
09/13/2018

Efficient Graph Cut Optimization for Full CRFs with Quantized Edges

Fully connected pairwise Conditional Random Fields (Full-CRF) with Gauss...
research
09/07/2018

ADM for grid CRF loss in CNN segmentation

Variants of gradient descent (GD) dominate CNN loss minimization in comp...
research
12/06/2019

End-to-end Training of CNN-CRF via Differentiable Dual-Decomposition

Modern computer vision (CV) is often based on convolutional neural netwo...
research
12/18/2014

Deep Structured Output Learning for Unconstrained Text Recognition

We develop a representation suitable for the unconstrained recognition o...

Please sign up or login with your details

Forgot password? Click here to reset