End-to-end Learning for Graph Decomposition

12/23/2018
by   Jie Song, et al.
0

We propose a novel end-to-end trainable framework for the graph decomposition problem. The minimum cost multicut problem is first converted to an unconstrained binary cubic formulation where cycle consistency constraints are incorporated into the objective function. The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials. The parameters of a standard Neural Network and the fully differentiable CRF are optimized in an end-to-end manner. Furthermore, our method utilizes the cycle constraints as meta-supervisory signals during the learning of the deep feature representations by taking the dependencies between the output random variables into account. We present analyses of the end-to-end learned representations, showing the impact of the joint training, on the task of clustering images of MNIST. We also validate the effectiveness of our approach both for the feature learning and the final clustering on the challenging task of real-world multi-person pose estimation.

READ FULL TEXT
research
07/29/2019

End-to-End Learning Deep CRF models for Multi-Object Tracking

Existing deep multi-object tracking (MOT) approaches first learn a deep ...
research
05/06/2019

Simulating CRF with CNN for CNN

Combining CNN with CRF for modeling dependencies between pixel labels is...
research
02/14/2012

Tightening MRF Relaxations with Planar Subproblems

We describe a new technique for computing lower-bounds on the minimum en...
research
12/11/2019

Bipartite Conditional Random Fields for Panoptic Segmentation

We tackle the panoptic segmentation problem with a conditional random fi...
research
12/10/2021

Optimizing Edge Detection for Image Segmentation with Multicut Penalties

The Minimum Cost Multicut Problem (MP) is a popular way for obtaining a ...
research
12/06/2016

Deep Stereo Matching with Dense CRF Priors

Stereo reconstruction from rectified images has recently been revisited ...
research
09/15/2022

Incremental cycle bases for cycle-based pose graph optimization

Pose graph optimization is a special case of the simultaneous localizati...

Please sign up or login with your details

Forgot password? Click here to reset