A network that learns to recognize three-dimensional objects

By Tomaso A. Poggio, Shimon Edelman. 1990

How researchers see this paper

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

Citations in the corpus

View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation (2016, positive): “Several hierarchical models of object recognition [17, 40, 43, 9] and face recognition [8, 29, 14] feature a progression from view-specific early processing stages to view-invariant later processing stages similar to ML/MF and AM, respectively.”
A self-organizing neural network architecture for learning human-object interactions (2017, background): “This capability resembles, to some extent, biological mechanisms for learning the three-dimensional objects in the human brain [47, 48, 7].”
A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information (1993, background): “One possibility, as advanced by Poggio and Edelman (1990), is that three-dimensional objects are actually represented by a few char-Concluding”
Coarse scales are sufﬁcient for efﬁcient categorization of emotional facial expressions: Evidence from neural computation (unknown): “Thus, authors have suggested using radial basis function (or RBF) networks consisting of Gaussian receptive ﬁelds which compress the information relating to various parts of an image [7,28].”
Unsupervised learning of invariant representations (2016, background): “The mathematics of the class-specific modules at the top of the hierarchy – with the underlying localization condition – justifies old models of viewpoint-invariant recognition (see [52]).”
Unsupervised Learning of Invariant Representations in Hierarchical Architectures (2013, background): “[18] is equivalent in the Fourier domain to”
What Object Attributes Determine Canonical Views? (1999, background): “In contrast, this is precisely the pattern predicted by theories of recognition in which views are determined by statistical learning methods over repeated exposures (Bricolo et al 1997; Poggio and Edelman 1990).”
3D Object Recognition: Symmetry and Virtual Views (1992, methodology): “These experiments are consistent with a network model proposed by Poggio and Edelman (1990), in which each hidden unit is similar to a view-centered neuron tuned to one of the example views (or to prototypical views) whereas the output can be view-independent if enough training views are provided.”
Learning Recognition and Segmentation Using the Cresceptron (1997, methodology): “Section 7 gives some concluding remarks.”
fMR-adaptation: a tool for studying the functional properties of human cortical neurons. (2001, background): “Some theories (e.g., Biederman, 1987) suggest a 3D objectcentered representation, while other theories suggest a viewer centered framework, such that 2D views of an object span its representation (e.g., Edelman & Duvdevani- Bar, 1997; Poggio & Edelman, 1990; Ullman, 1996).”
Generalization and similarity in exemplar models of categorization: Insights from machine learning (2008, methodology): “Clearly, under these condi-268 has been suggested in the object recognition literature (Poggio & Edelman, 1990) and is emphasized in several categorization models (Love et al., 2004; Rosseel, 2002; Verguts, Ameel, & Storms, 2004).”
Invariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet (2012, background): “One of the factors that will influence the performance of the type of architecture considered here, hierarchically organized series of competitive networks, which form one class of approaches to biologically relevant networks for invariant object recognition (Fukushima, 1980; Poggio and Edelman, 199”
Learning viewpoint invariant object representations using a temporal coherence principle (2005, background): ““Image-based” or “view-based” models in turn postulate the existence of a small number of two-dimensional templates for objects and propose several mechanisms that could allow generalization to novel viewpoints, such as mental rotation (Tarr and Pinker 1989), mapping to a standard (“canonical”) view”
Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning? (2013, background): “The mathematics of the class-speciﬁc modules at the top of the hierarchy – with the underlying localization condition – justiﬁes old models of viewpoint-invariant recognition (see [52]).”