Help Privacy Policy Disclaimer
  Advanced SearchBrowse





End-to-end Learning for Graph Decomposition


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

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

(Preprint), 3MB

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

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: https://hdl.handle.net/21.11116/0000-0005-64CF-2
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.