TY - JOUR

T1 - Deep visual unsupervised domain adaptation for classification tasks: a survey

AU - Madadi, Yeganeh

AU - Seydi, Vahid

AU - Nasrollahi, Kamal

AU - Hosseini, Reshad

AU - Moeslund, Thomas B

PY - 2020/12/1

Y1 - 2020/12/1

N2 - Learning methods are challenged when there is not enough labelled data. It gets worse when the existing learning data have different distributions in different domains. To deal with such situations, deep unsupervised domain adaptation techniques have newly been widely used. This study surveys such domain adaptation methods that have been used for classification tasks in computer vision. The survey includes the very recent papers on this topic that have not been included in the previous surveys and introduces a taxonomy by grouping methods published on unsupervised domain adaptation into five groups of discrepancy-, adversarial-, reconstruction-, representation-, and attention-based methods.

AB - Learning methods are challenged when there is not enough labelled data. It gets worse when the existing learning data have different distributions in different domains. To deal with such situations, deep unsupervised domain adaptation techniques have newly been widely used. This study surveys such domain adaptation methods that have been used for classification tasks in computer vision. The survey includes the very recent papers on this topic that have not been included in the previous surveys and introduces a taxonomy by grouping methods published on unsupervised domain adaptation into five groups of discrepancy-, adversarial-, reconstruction-, representation-, and attention-based methods.

U2 - 10.1049/iet-ipr.2020.0087

DO - 10.1049/iet-ipr.2020.0087

M3 - Erthygl

VL - 14

SP - 3283

EP - 3299

JO - IET Image Processing

JF - IET Image Processing

IS - 14

ER -