RT Journal Article
T1 Multi-domain Adversarial Variational Bayesian Inference for Domain Generalization
A1 Gao, Zhifan
A1 Guo, Saidi
A1 Xu, Chenchu
A1 Zhang, Jinglin
A1 Gong, Mingming
A1 Del Ser, Javier
A1 Li, Shuo
AB Domain generalization aims to learn common knowledge from multiple observed source domains and transfer it to unseen target domains, e.g. the object recognition in varieties of visual environments. Traditional domain generalization methods aim to learn the feature representation of the raw data with its distribution invariant across domains. This relies on the assumption that the two posterior distributions (the distributions of the label given the feature distribution and given the raw data) are stable in different domains. However, this does not always hold in many practical situations. In this paper, we relax the above assumption by permitting the posterior distribution of the label given the raw data changes in difference domains, and thus focuses on a more realistic learning problem that infers the conditional domain-invariant feature representation. Specifically, a multi-domain adversarial variational Bayesian inference approach is proposed to minimize the inter-domain discrepancy of the conditional distributions of the feature given the label. Besides, it is imposed by the constraints from the adversarial learning and feedback mechanism to enhance the condition invariant feature representation. The extensive experiments on two datasets demonstrate the effectiveness of our approach, as well as the state-of-the-art performance comparing with thirteen methods.
SN 1051-8215
YR 2022
FD 2022
LK https://hdl.handle.net/11556/4171
UL https://hdl.handle.net/11556/4171
LA eng
NO Gao , Z , Guo , S , Xu , C , Zhang , J , Gong , M , Del Ser , J & Li , S 2022 , ' Multi-domain Adversarial Variational Bayesian Inference for Domain Generalization ' , IEEE Transactions on Circuits and Systems for Video Technology , pp. 1 . https://doi.org/10.1109/TCSVT.2022.3232112
NO Publisher Copyright: IEEE
DS TECNALIA Publications
RD 31 jul 2024