A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex

By Thomas Serre, Minjoon Kouh, Charles F. Cadieu, Ulf Knoblich, Gabriel Kreiman, Tomaso A. Poggio. 2005

332 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e5baffdda5c5175ad9d71e2d21703298b84cffe8

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

Trade-Off between Object Selectivity and Tolerance in Monkey Inferotemporal Cortex (2007, unknown): “Monkey Inferotemporal Cortex”
Unsupervised learning of invariant representations (2016, background): “one-layer networks [25] because they provide signatures for image patches of several sizes and locations.”
Computational role of eccentricity dependent cortical magnification (2014, result): “This picture is consistent with the invariance found in IT cells ([15]).”
Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning? (2013, background): “[19] in general is not true.”
A Canonical Neural Circuit for Cortical Nonlinear Operations (2008, methodology): “See Kouh (2007) and Serre et al. (2005) for a comprehensive description of the current, recently extended version of the model and Riesenhuber and Poggio (1999) for the original proposal.”
Recent Advances in Physical Reservoir Computing: A Review (2018, background): “…that the primary visual cortex can perform timedependent computation for sequential inputs based on memory mechanisms is in contrast to the conventional one that it executes frame-by-frame computation based on memory-less hierarchically organized feedforward architectures (Serre et al., 2005).”
Robust Object Recognition with Cortex-Like Mechanisms (2007, methodology): “Our system follows a recent theory of the feedforward path of object recognition in cortex that accounts for the first 100-200 milliseconds of processing in the ventral stream of primate visual cortex [14], [15].”
Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity (2007, methodology): “This ﬁnal potential can be seen as the number of early spikes in common between a current input and a stored prototype (this contrasts with HMAX and extensions [6,7,26], where a Euclidian distance or a normalized dot product is used to measure the difference between a stored prototype Figure 1.”
Convex multi-task feature learning (2008, background): “Images of different objects may share a number of features that are different from the pixel representation of images (Heisele et al. 2002; Serre et al. 2005; Torralba et al. 2004).”
Unsupervised Learning of Invariant Representations in Hierarchical Architectures (2013, background): “Hierarchical architectures are better at recognition in clutter than one-layer networks [51], because they provide signatures for image patches of several sizes and locations.”
A quantitative theory of immediate visual recognition. (2007, methodology): “We used a one-versus-all approach, training eight binary classifiers , one for each category against the rest of the categories, and then taking the classifier prediction to be the maximum among the eight classifiers (for further details, see Hung et al., 2005; Serre et al., 2005).”
Hierarchical learning : theory with applications in speech and vision (2009, background): “theoretical foundation explaining recent models designed on the basis of anatomical and physiological data describing the primate visual cortex [96, 94].”