Year: 2014
Type: conference-paper
Abstract: This work considers the on-the-fly domain adaptation of supervised binary classifiers, learned off-line, in order to adapt them to a target context.The probability density functions associated to negative and positive classes are supposed to be mixtures of the source distributions.Moreover, the mixture weights and the priors are only available at runtime.We present a theoretical solution to this problem, and demonstrate the effectiveness of the proposed approach on a real computer vision application.Our theoretical solution is applicable to any classifier approximating Bayes' classifier.z 1,1 z 1,2 z 1,3 z 1,4 z 2,1 z 2,2 z 2,3 z 2,4 z 3,1 z 3,2 z 3,3 z 3,4 z 4,1 z 4,2 z 4,3 z 4,4 z 5,1 z 5,2 z 5,3 z 5,4 (a) example 1 z 1,1 z 1,2 z 1,3 z 1,4 z 2,1 z 2,2 z 2,3 z 2,4 z 3,1 z 3,2 z 3,3 z 3,4 z 4,1 z 4,2 z 4,3 z 4,4 z 5,1 z 5,2 z 5,3 z 5,4 (b) example 2 z 1,1 z 1,2 z 1,3 z 1,4 z 2,1 z 2,2 z 2,3 z 2,4 z 3,1 z 3,2 z 3,3 z 3,4 z 4,1 z 4,2 z 4,3 z 4,4 z 5,1 z 5,2 z 5,3 z 5,4 (c) example 3 Figure 1.The γ -× γ + models are highly dependent.This figure represents their outputs for γ -= 5 and γ + = 4. Three sets of dependent predictions are highlighted in gray (it is assumed that zk,l ∈ (0, 1)).Each highlighted value can be determined from the other ones.z 1,1 z 1,2 z 1,3 z 1,4 z 2,1 z 2,2 z 2,3 z 2,4 z 3,1 z 3,2 z 3,3 z 3,4 z 4,1 z 4,2 z 4,3 z 4,4 z 5,1 z 5,2 z 5,3 z 5,4 (a) example 1 z 1,1 z 1,2 z 1,3 z 1,4 z 2,1 z 2,2 z 2,3 z 2,4 z 3,1 z 3,2 z 3,3 z 3,4 z 4,1 z 4,2 z 4,3 z 4,4 z 5,1 z 5,2 z 5,3 z 5,4 (b) example 2
Institution: University of Liège
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W244169709