Models of object recognition

By Maximilian Riesenhuber, Tomaso A. Poggio. Nature Neuroscience, 2000

735 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b44a278ceccabc60548f2959d43a1f258d38f55d

How researchers see this paper

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

In Cognitive Neuroscience

Citations in the corpus

A neurodynamical cortical model of visual attention and invariant object recognition. (2004, methodology): “Recently, Rolls, Aggelopoulos, and Zheng (2004) (see also Rolls & Deco, 2002) investigated how information is passed from the inferior temporal cortex (IT) to other brain regions to enable stimuli presented in complex natural scenes to be selected for action.”
How long to get to the “gist” of real-world natural scenes? (2005, background): “Following such a view, objects would be processed almost systematically before the scene (Biederman, 1987; Riesenhuber & Poggio, 2000).”
Unsupervised Learning of Invariant Representations in Hierarchical Architectures (2013, background): “This is the insight underlying many networks for visual recognition, including HMAX [32] and convolutional neural nets [33, 34].”
Realistic Modeling of Simple and Complex Cell Tuning in the HMAX Model, and Implications for Invariant Object Recognition in Cortex (2004, methodology): “The mechanisms rely on a non-linear MAX operation (or its soft-MAX approximation, [14]) over properly chosen afferents, i.”
Why Does Deep and Cheap Learning Work So Well? (2016, background): “In neuroscience parlance, the functions fi compress the data into forms with ever more invariance [28], containing features invariant under irrelevant transformations (for example background substitution, scaling and translation).”
Modeling the influence of task on attention. (2005, background): “2000)), and other factors (for reviews, see Arman & Aggarwal, 1993; Riesenhuber & Poggio, 2000 ).”
A neural theory of visual attention: bridging cognition and neurophysiology. (2005, background): “…proposing a computational account of position and size invariance in visual recognition (for different approaches, see Heinke & Humphreys, 2003; Riesenhuber & Poggio, 2000; see also Fukushima, 1980; Larsen & Bundesen, 1978, 1998), we assume (a) that the effective RF can vary in position…”
Finding a roadmap to achieve large neuromorphic hardware systems (2013, background): “…input representations are important for neural computation, and some have done some interesting engineering work based on these front-end systems (Riesenhuber and Poggio, 2000; Fu et al., 2008; Schaik et al., 2009; Chakrabartty and Liu, 2010; Liu and Delbruck, 2010; Farabet et al., 2011;…”
Do early sensory cortices integrate cross-modal information? (2007, background): “Such intra-modal combinations often result in responses that reach about the average response of both features presented in isolation (Riesenhuber and Poggio 2000).”
Unsupervised learning of invariant representations (2016, background): “This is the insight underlying many networks for visual recognition, including HMAX [2] and convolutional neural nets [3] [4].”
A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex (2005, methodology): “Computationally, there is no difference between categorization and identification (see [Riesenhuber and Poggio, 2000]).”
Trade-Off between Object Selectivity and Tolerance in Monkey Inferotemporal Cortex (2007, methodology): “This model uses layers of neural units in a feedforward hierarchy, tuned to produce a gradual buildup of selectivity (AND-like operations) and tolerance (OR-like operations) (Fukushima, 1980; Perrett and Oram, 1993; Wallis and Rolls, 1997; Riesenhuber and Poggio, 1999, 2000).”
Object Detection (2020, background): “A typical example is the MAX operation [11,1].”
The role of single neurons in information processing (2000, methodology): “The MAX operation discussed in this issue by Riesenhuber and Poggi”