English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

End-to-end Learning for Graph Decomposition

MPS-Authors
/persons/resource/persons98382

Andres,  Bjoern
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

External Ressource
No external resources are shared
Fulltext (public)

arXiv:1812.09737.pdf
(Preprint), 3MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Song, J., Andres, B., Black, M., Hilliges, O., & Tang, S. (2018). End-to-end Learning for Graph Decomposition. Retrieved from http://arxiv.org/abs/1812.09737.


Cite as: http://hdl.handle.net/21.11116/0000-0005-64CF-2
Abstract
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.