Bayesian Visual Inference and Attention

The massive amount of visual inputs could easily go beyond the system’s computational limit. Visual attention provides an efficient way to discard the trivial inputs and achieve good performance. In this paper we develop a unified and consistent theoretical framework for the visual attention and inference with Bayesian decision theory. A visual attention scheme is simulated with an artificial retina mimicking biological ones. We test our model on a real world video clip. The experimental results indicate the promise of this visual attention model in complicated vision applications.

[1]  W. Richards,et al.  Perception as Bayesian Inference , 2008 .

[2]  Rajesh P. N. Rao,et al.  Probabilistic Models of the Brain: Perception and Neural Function , 2002 .

[3]  Alan L. Yuille,et al.  Ideal Observers for Detecting Motion: Correspondence Noise , 2005, NIPS.

[4]  A. Yuille,et al.  Object perception as Bayesian inference. , 2004, Annual review of psychology.

[5]  J T Todd,et al.  Ambiguity and the ‘Mental Eye’ in Pictorial Relief , 2001, Perception.

[6]  Laurent Itti,et al.  Congruence between model and human attention reveals unique signatures of critical visual events , 2007, NIPS.

[7]  D. Kersten,et al.  Three-dimensional symmetric shapes are discriminated more efficiently than asymmetric ones. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[8]  T. Albright,et al.  Contextual influences on visual processing. , 2002, Annual review of neuroscience.

[9]  Song-Chun Zhu,et al.  Embedding Gestalt Laws in Markov Random Fields , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Paul R. Schrater,et al.  Pattern inference theory: A probabilistic approach to vision , 2002 .

[11]  Pierre Baldi,et al.  Bayesian surprise attracts human attention , 2005, Vision Research.

[12]  Rajesh P. N. Rao,et al.  Bayesian inference and attentional modulation in the visual cortex , 2005, Neuroreport.

[13]  D. Kersten,et al.  Illusions, perception and Bayes , 2002, Nature Neuroscience.

[14]  Alan L. Yuille,et al.  Probabilistic Motion Estimation Based on Temporal Coherence , 2000, Neural Computation.

[15]  Michael C. Mozer,et al.  Top-Down Control of Visual Attention: A Rational Account , 2005, NIPS.

[16]  Song-Chun Zhu,et al.  Minimax Entropy Principle and Its Application to Texture Modeling , 1997, Neural Computation.

[17]  Li Zhaoping,et al.  Filling-In and Suppression of Visual Perception from Context: A Bayesian Account of Perceptual Biases by Contextual Influences , 2007, PLoS computational biology.

[18]  Z. Pizlo.  Perception viewed as an inverse problem , 2001, Vision Research.