Maximum Differentiation (MAD) Competition Zhou Wang and Eero
P. Simoncelli
|
|
MAD competition is an efficient methodology for
comparing computational models of a perceptually discriminable quantity.� Rather than pre-selecting test stimuli for
subjective evaluation and comparison to the models, stimuli are synthesized so as to optimally distinguish the models.� Specifically, we first synthesize a pair of
stimuli that maximize/minimize one model while holding the other fixed.� We then repeat this procedure, but with the
roles of the two models reversed.�
Subjective testing on pairs of such synthesized stimuli provides a
strong indication of the relative strengths and weaknesses of the two
models.� Careful study of the stimuli
may, in turn, suggest potential ways to improve a model or to combine aspects
of multiple models. We demonstrate the methodology using two examples: contrast
perception and perceptual image quality assessment.
Demonstration:
MAD competition between two full-reference image
quality assessment models: Mean squared error (MSE) and Structural Similarity Index (SSIM)
Synthesizing maximum/minimum SSIM
images along the equal-MSE contour in the image space:
Synthesizing maximum/minimum SSIM
images at different MSE levels:
Reference:
Zhou Wang and Eero P. Simoncelli, "Maximum
differentiation (MAD) competition: A methodology for comparing computational
models of perceptual discriminability," Journal of Vision, vol. 8, no. 12, pp. 1-13, Sept.
2008.
Created
Nov. 21, 2007, Updated Sept. 25, 2008