Domain Adaptation Metric Learning

Domain adaptation in distance metric learning but neither learns a representation space capable of separating the source and target domains.

Domain adaptation metric learning. In this paper we show that this does not always hold. Unsupervised domain adaptation is a promising avenue to enhance the performance of deep neural networks on a target domain using labels only from a source domain. We provide extensive experimental results on real world datasets to both demonstrate the effectiveness of metric learning for graph construction for domain adaptation and analyze the contributions of each component.

Many existing da methods assume that a low source risk together with the alignment of distributions of source and target means a low target risk. On the other hand jmfl reveals the shared underlying factors between the two domains to learn a new feature representation. However the two predominant methods domain discrepancy reduction learning and semi supervised learning are not readily applicable when source and target domains do not share a common label space.

For example si et al. Metric learning methods learn a metric to measure the distribution divergence between the source domain and the target domain and then reduce the divergence by minimizing the metric. Metric learning in optimal transport for domain adaptation tanguy kerdoncuff remi emonet and marc sebban univ lyon ujm saint etienne cnrs institut d optique graduate school laboratoire hubert curien umr 5516 f 42023 saint etienne france ftanguy kerdoncuff remi emonet marc sebbang univ st etienne fr abstract.

The state of the art metric learning algorithms cannot perform well for domain adaptation settings such as cross domain face recognition image annotation etc because labeled data in the source domain and unlabeled ones in the target domain are drawn from different but related distributions. We thus propose a novel metric learning assisted domain adaptation mla da method which employs a novel triplet. Resembling cd2ma luo et al 2017 considers domain adaptation with disjoint label spaces but the problem is still cast as classification with an assumption.

Specifically we present joint metric and feature representation learning jmfl for unsupervised domain adaptation. Several methods for domain adaptation have recently been proposed arnold et al 2008. Domain alignment da has been widely used in unsupervised domain adaptation.

Jmfl on the one hand minimizes the domain discrepancy between the source domain and the target domain. The state of the art metric learning algorithms cannot perform well for domain adaptation settings such as cross domain face recognition image annotation etc because labeled data in the source domain and unlabeled ones in the target domain are drawn from different but related distributions.