Corpus ID: 14639343

Complexity of Representation and Inference in Compositional Models with Part Sharing

@article{Yuille2016ComplexityOR,
  title={Complexity of Representation and Inference in Compositional Models with Part Sharing},
  author={A. Yuille and R. Mottaghi},
  journal={J. Mach. Learn. Res.},
  year={2016},
  volume={17},
  pages={11:1-11:28}
}
This paper performs a complexity analysis of a class of serial and parallel compositional models of multiple objects and shows that they enable efficient representation and rapid inference. Compositional models are generative and represent objects in a hierarchically distributed manner in terms of parts and subparts, which are constructed recursively by part-subpart compositions. Parts are represented more coarsely at higher level of the hierarchy, so that the upper levels give coarse summary… Expand
Probabilistic Compositional Active Basis Models for Robust Pattern Recognition
From Red Wine to Red Tomato: Composition with Context
Visual Concepts and Compositional Voting
3D compositional hierarchies for object categorization
Towards deep compositional networks
The Visual System's Internal Model of the World
  • T. Lee
  • Computer Science, Medicine
  • Proceedings of the IEEE
  • 2015
Sampling-Tree Model: Efficient Implementation of Distributed Bayesian Inference in Neural Networks
Visual Shape Perception as Bayesian Inference of 3D Object-Centered Shape Representations
...
1
2
...

References

SHOWING 1-10 OF 37 REFERENCES
Part and appearance sharing: Recursive Compositional Models for multi-view
Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion
Inference and Learning with Hierarchical Shape Models
Towards a theory of compositional learning and encoding of objects
  • A. Yuille
  • Computer Science
  • 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)
  • 2011
Dynamic trees for image modelling
Single Units and Visual Cortical Organization
A Computational Perspective on Visual Attention
Robust Object Recognition with Cortex-Like Mechanisms
Modeling Image Patches with a Generic Dictionary of Mini-epitomes
Recognition-by-components: a theory of human image understanding.
...
1
2
3
4
...