Bayesian models of object perception.

By Daniel J. Kersten, Alan L. Yuille. Current Opinion in Neurobiology, 2003

300 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/8efb5649d69331471fbb9152b638fb2d610e65fd

How researchers see this paper

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

In Atomic and Molecular Physics, and Optics

In Cognitive Neuroscience

Citations in the corpus

On the assessment of landmark salience for human navigation (2007, background): “Probabilistic inference models are increasingly becoming important theoretical tools for understanding cognition (Chater et al. 2006; Scholl and Tremoulet 2000; Kersten and Yuille 2003; Kersten et al. 2004).”
Bayesian decision theory in sensorimotor control. (2006, unknown): “Within this framework many illusions and other visual effects can be understood [18] by making general assumptions about priors over possible visual objects [ 19 ,20] or the direction of illumination [21,22].”
Real-time classification and sensor fusion with a spiking deep belief network (2013, background): “This is consistent with a variety of theories that the brain encodes Bayesian generative models of its natural environment (Kersten and Yuille, 2003; Knill and Pouget, 2004).”
Bursting of thalamic neurons and states of vigilance. (2006, background): “…extensive corticothalamic recurrence and temporal binding properties, may be viewed as creating the complex combinatorial sensory-motor landscape (Kersten and Yuille 2003; Llinás 2001; Mountcastle 1998, 2005; Steriade 2001a) required for the elaboration of the intentionality that characterizes…”
Object perception as Bayesian inference. (2004, background): “Recent work (Freeman & Pasztor 1999,Schrater & Kersten 2000,Kersten & Yuille 2003) has shown how specifying generative models in terms of in(cid:13)uence graphs (or \Bayesian networks", Pearl 1988), together with a description of visual tasks, allow us to break problems down into categories (see…”
The Innate Mind: Structure and Contents (2005, background): “…evidence suggests that the visual system does engage in ‘‘unconscious inference’’ in accord with Bayes’ theorem (for reviews see Kersten et al., 2004; Kersten & Yuille, 2003; Knill & Richards, 1996; Mamassian et al., 2002).6 In the context of visual perception, the data consist of the visual…”
How Prediction Errors Shape Perception, Attention, and Motivation (2012, background): “In these models, predictions of impending perceptual events help us quickly interpret and disambiguate noisy and ambiguous input (Kersten and Yuille, 2003; Sterzer et al., 2008).”
Computational mechanisms of sensorimotor control. (2011, unknown): “Bayesian integration can also explain many visual illusions by making assumptions about the priors over visual objects (Kersten and Yuille, 2003) or direction of illumination (Adams et al.”
Probabilistic Inference in General Graphical Models through Sampling in Stochastic Networks of Spiking Neurons (2011, background): “For example, it has been shown that human visual perception involves ‘‘explaining away’’, a well known effect in probabilistic inference, where a change in the probability of one competing hypothesis for explaining some observation affects the probability of another competing hypothesis [20].”
When the world becomes 'too real': a Bayesian explanation of autistic perception. (2012, methodology): “Bayesian statistical decision theory, a principled method of optimal reasoning under uncertainty, formalizes Helmoltz’s and Gregory’s notions of perception as unconscious inference [34-37].”
A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs (2017, background): “Many researchers have conjectured that this could be achieved by incorporating the inductive biases of the visual cortex ( 9 – 12 ), utilizing the wealth of data generated by neuroscience and cognitive science research.”
1 On what it means to see , and what we can do about it (2008, unknown): “…the gradual realization that the prime candidate framework for managing uncertainty — graphical models, or Bayes networks — is ubiquitous in biological vision (Kersten et al., 2004; Kersten and Yuille, 2003; Knill and Richards, 1996), as it is, indeed, in cognition in general (Chater et al., 2006).”
Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. (2006, background): “Recent behavioral and modeling research suggests that early scene interpretation may be influenced by global image properties that are computed by processes that do not require selective visual attention (Spatial Envelope properties of a scene, Oliva & Torralba, 2001, statistical properties of objec”