Learning Iterative Image Reconstruction in the Neural Abstraction Pyramid

By Sven Behnke. 2001

21 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deep Generative Stochastic Networks Trainable by Backprop (2013, background): “…graph allows information to propagate both upwards (from input to higher levels) and downwards, giving rise to the computational graph structure illustrated in Figure 3, which is similar to that explored for deterministic recurrent auto-encoders (Seung, 1998; Behnke, 2001; Savard, 2011).”
GSNs : Generative Stochastic Networks (2015, background): “5, which is similar to that explored for deterministic recurrent autoencoders (Behnke, 2001; Savard, 2011; Seung, 1998).”
Deep learning in neural networks: An overview (2014, methodology): “Hierarchical CNNs in a Neural Abstraction Pyramid (e.g., Behnke, 2003b, 2005) were trained to reconstruct images corrupted by structured noise (Behnke, 2001), thus enforcing increasingly abstract image representations in deeper and deeper layers.”
Tagger: Deep Unsupervised Perceptual Grouping (2016, neutral): “mbiguities and feedback connections that allow incorporation of high-level information. In early pioneering work the NAP was trained for iterative image binarization [5] and iterative image denoising [4], much akin to the setup we use. Being recurrent, the NAP layers too, could in principle learn a ”
Deep Networks with Internal Selective Attention through Feedback Connections (2014, methodology): “Iterative processing of images using recurrency has been successfully used for image reconstruction [48], face-localization [49] and compression [50].”
Learning Face Localization Using Hierarchical Recurrent Networks (2002, methodology): “To accelerate the training, we initially worked with randomly chosen subsets of the training set, as described in [ 2 ].”
Binding via Reconstruction Clustering (2015, methodology): “Alternative approaches to the binding problem proposed in the literature are discussed in Section 5.”