Open AccessProceedings Article
Learning to Parse Images
Geoffrey E. Hinton,Zoubin Ghahramani,Yee Whye Teh +2 more
- Vol. 12, pp 463-469
Reads0
Chats0
TLDR
Using parse trees as internal representations of images, credibility networks are able to perform segmentation and recognition simultaneously, removing the need for ad hoc segmentation heuristics.Abstract:
We describe a class of probabilistic models that we call credibility networks. Using parse trees as internal representations of images, credibility networks are able to perform segmentation and recognition simultaneously, removing the need for ad hoc segmentation heuristics. Promising results in the problem of segmenting handwritten digits were obtained.read more
Citations
More filters
Proceedings Article
Dynamic Routing Between Capsules
TL;DR: It is shown that a discrimininatively trained, multi-layer capsule system achieves state-of-the-art performance on MNIST and is considerably better than a convolutional net at recognizing highly overlapping digits.
Book ChapterDOI
Multi-class Open Set Recognition Using Probability of Inclusion
TL;DR: The problem is formulated as one of modeling positive training data at the decision boundary, where the statistical extreme value theory can be invoked, and a new algorithm called the P I -SVM is introduced for estimating the unnormalized posterior probability of class inclusion.
Proceedings ArticleDOI
Context and Hierarchy in a Probabilistic Image Model
Ya Jin,Stuart Geman +1 more
TL;DR: A mathematical framework for constructing probabilistic hierarchical image models, designed to accommodate arbitrary contextual relationships, is proposed, and a demonstration system for reading Massachusetts license plates in an image set collected at Logan Airport is built.
Dissertation
Graphical models for visual object recognition and tracking
TL;DR: The approach couples topic models originally developed for text analysis with spatial transformations, and thus consistently accounts for geometric constraints by building integrated scene models, which may discover contextual relationships, and better exploit partially labeled training images.
Journal ArticleDOI
Describing Visual Scenes Using Transformed Objects and Parts
TL;DR: This work develops hierarchical, probabilistic models for objects, the parts composing them, and the visual scenes surrounding them and proposes nonparametric models which use Dirichlet processes to automatically learn the number of parts underlying each object category, and objects composing each scene.
References
More filters
Journal ArticleDOI
Maximum likelihood from incomplete data via the EM algorithm
Book ChapterDOI
Learning internal representations by error propagation
TL;DR: This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion.
Book
Learning internal representations by error propagation
TL;DR: In this paper, the problem of the generalized delta rule is discussed and the Generalized Delta Rule is applied to the simulation results of simulation results in terms of the generalized delta rule.
Journal ArticleDOI
Backpropagation applied to handwritten zip code recognition
Yann LeCun,Bernhard E. Boser,John S. Denker,D. Henderson,Richard Howard,W. Hubbard,Lawrence D. Jackel +6 more
TL;DR: This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
Book
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
TL;DR: Marr's posthumously published Vision (1982) influenced a generation of brain and cognitive scientists, inspiring many to enter the field of visual perception as discussed by the authors, where the process of vision constructs a set of representations, starting from a description of the input image and culminating with three-dimensional objects in the surrounding environment, a central theme and one that has had farreaching influence in both neuroscience and cognitive science, is the notion of different levels of analysis.