In this paper, we tackle the problem of reducing discrepancies between multiple domains, i.e. multi-source domain adaptation, and consider it under the target shift assumption: in all domains we aim to solve a classification problem with the same output classes, but with different labels proportions. This problem, generally ignored in the vast majority of domain adaptation papers, is nevertheless critical in real-world applications, and we theoretically show its impact on the success of the adaptation. Our proposed method is based on optimal transport, a theory that has been successfully used to tackle adaptation problems in machine learning. The introduced approach, Joint Class Proportion and Optimal Transport (JCPOT), performs multi-source adaptation and target shift correction simultaneously by learning the class probabilities of the unlabeled target sample and the coupling allowing to align two (or more) probability distributions. Experiments on both synthetic and real-world data (satellite image pixel classification) task show the superiority of the proposed method over the state-of-the-art.
|Publication status||Published - 2020|
|Event||22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 - Naha, Japan|
Duration: 16 Apr 2019 → 18 Apr 2019
|Conference||22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019|
|Period||16/04/19 → 18/04/19|