DeepAI AI Chat
Log In Sign Up

Simulating CRF with CNN for CNN

by   Lena Gorelick, et al.

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.


page 6

page 7

page 9

page 11

page 14


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...

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

We propose a novel and principled hybrid CNN+CRF model for stereo estima...

End-to-end Learning for Graph Decomposition

We propose a novel end-to-end trainable framework for the graph decompos...

Efficient Graph Cut Optimization for Full CRFs with Quantized Edges

Fully connected pairwise Conditional Random Fields (Full-CRF) with Gauss...

ADM for grid CRF loss in CNN segmentation

Variants of gradient descent (GD) dominate CNN loss minimization in comp...

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

Modern computer vision (CV) is often based on convolutional neural netwo...

Non-Standard Vietnamese Word Detection and Normalization for Text-to-Speech

Converting written texts into their spoken forms is an essential problem...