Deep visual unsupervised domain adaptation for classification tasks: a survey

Yeganeh Madadi, Vahid Seydi, Kamal Nasrollahi, Reshad Hosseini, Thomas B. Moeslund
2020 IET Image Processing  
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
more » ... nd introduces a taxonomy by grouping methods published on unsupervised domain adaptation into five groups of discrepancy-, adversarial-, reconstruction-, representation-, and attention-based methods. Partial adversarial-based methods partial adversarial networks SAN [89], PADA [90], IWAN [91], ETN [92] Bold highlights three particular approaches. Fig. 7 t-SNE [178] embeddings of 1000 test samples from SVHN (source, red) and MNIST (target, blue) (a) MMD metric, (b) TarGAN method [69]
doi:10.1049/iet-ipr.2020.0087 fatcat:x7v5et3r6nagpe2ivuu5nd4qku