Neural abstraction pyramid: a hierarchical image understanding architecture

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep learning in neural networks: An overview (2014, background): “Compare earlier RNNs for object recognition through iterative image interpretation (Behnke and Rojas, 1998; Behnke, 2002, 2003b); see also more recent publications (Wyatte et al.”
Multigrid Neural Architectures (2016, methodology): “Our work differs from these and earlier models [2] by virtual of decoupling pyramid level from feature abstraction.”
Learning Iterative Image Reconstruction in the Neural Abstraction Pyramid (2001, methodology): “The neural abstraction pyramid architecture, introduced in [Behnke and Rojas, 1998], is a suitable framework for iterative image reconstruction.”
Hebbian learning and competition in the neural abstraction pyramid (1999, background): “Furthermore, we plan to apply the Neural Abstraction Pyramid approach to more complex image interpretation problems like face recognition and object segmentation.”
Learning Face Localization Using Hierarchical Recurrent Networks (2002, methodology): “The preprocessed images are presented to a hierarchical neural network that is structured as Neural Abstraction Pyramid [ 1 ].”
Face localization and tracking in the neural abstraction pyramid (2005, unknown): “The preprocessed images are presented to a Neural Abstraction Pyramid [4,3].”