Learning the 2-D Topology of Images

22 citations recorded by the source corpus.

How researchers see this paper

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

Deep Convolutional Networks on Graph-Structured Data (2015, background): “While correlations are typically sufﬁcient to reveal the intrinsic geometrical structure of images [16], the effects of higher-order statistics might be non-negligible in other contexts, especially in presence of sparsity.”
Representation Learning: A Review and New Perspectives (2012, background): “In fact, these dependencies can be exploited to discover the topology [126], i.”
Geometric Deep Learning: Going beyond Euclidean data (2016, methodology): “When applied to natural images represented as graphs with weights defined by the covariance, the spectral CNN construction recovers the standard CNN, without any prior knowledge [76].”